© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 81331
    Prev
    Next
    INDEX
    Explanations

    list and layout components

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron identifies programming‐related tokens and code snippets (e.g. code keywords, identifiers, numbers, and API/class names) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    programming Q&A content, especially mobile app development discussions with code snippets, technical terms, and UI/layout or API/networking details.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    code snippets and programming-related content, particularly in technical question-and-answer contexts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Crit
    -0.81
     seawater
    -0.76
    蠟
    -0.74
    难得
    -0.73
     infrequent
    -0.73
    凪
    -0.72
    Crit
    -0.68
    尷
    -0.67
    ventana
    -0.66
     rare
    -0.65
    POSITIVE LOGITS
     AIA
    1.03
    thunk
    0.96
     Kod
    0.91
     Thon
    0.91
     Companion
    0.88
    Companion
    0.85
    Kod
    0.84
    oltán
    0.83
     Components
    0.83
    Components
    0.82
    Activations Density 0.028%

    No Known Activations