© 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. 89728
    Prev
    Next
    INDEX
    Explanations

    code file paths

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

    This neuron responds to file‐path strings in code (e.g. import/include paths with slash-separated segments and a filename).

    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
    слова
    -0.83
    ὕ
    -0.81
     /[
    -0.75
    Glit
    -0.73
    десь
    -0.72
    シブル
    -0.72
    licherweise
    -0.71
    Maestro
    -0.71
     cadres
    -0.69
    Ehr
    -0.69
    POSITIVE LOGITS
    rlr
    0.93
     promedio
    0.89
    Damn
    0.88
    Average
    0.79
     presque
    0.77
     Average
    0.77
     Gone
    0.75
     conversational
    0.75
     إلى
    0.74
    ęgn
    0.74
    Activations Density 0.013%

    No Known Activations