© 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. 83165
    Prev
    Next
    INDEX
    Explanations

    competed or succeeded

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

    The neuron activates on programming-language keywords and tokens (e.g. include/require directives, function calls, special punctuation) in code snippets.

    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
    锺
    -0.75
    ination
    -0.73
     boulevard
    -0.73
     Boulevard
    -0.73
    糞
    -0.71
     nobles
    -0.69
     شیک
    -0.69
     setw
    -0.69
     Nguyên
    -0.68
    blower
    -0.68
    POSITIVE LOGITS
    yentes
    0.91
    failed
    0.86
    FAILED
    0.85
     FAILED
    0.83
     opak
    0.80
    ötä
    0.79
     succeeded
    0.78
     исследование
    0.78
    فحة
    0.77
     fikk
    0.76
    Activations Density 0.000%

    No Known Activations