© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 84306
    Prev
    Next
    INDEX
    Explanations

    URLs, tutorials, and code snippets

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

    The neuron is triggered by file-name tokens and other standalone identifiers in documentation or code (e.g. “No”, “direct”, “sip.js.md”, version numbers like “12”), i.e. it picks out isolated resource names or key identifiers.

    oai_token-act-pair · o4-miniTriggered 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
     stavu
    -0.79
     Standardization
    -0.77
     потому
    -0.73
     orgánica
    -0.70
    oidal
    -0.70
    aluno
    -0.67
    standalone
    -0.67
    ///<
    -0.66
    vium
    -0.66
     тво
    -0.65
    POSITIVE LOGITS
     pharmacy
    0.81
    apkamer
    0.81
    SPECTION
    0.73
    Energie
    0.71
    ἅ
    0.71
    帑
    0.70
    richt
    0.69
    banken
    0.69
     Fighting
    0.68
     Woodland
    0.68
    Activations Density 0.037%

    No Known Activations