© 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. 55832
    Prev
    Next
    INDEX
    Explanations

    code or file generation

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

    The neuron fires strongly on boilerplate “auto‐generated” code header comments (e.g. lines like “This code was generated by a tool”).

    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
     SERIES
    -0.83
    SERIES
    -0.81
    Series
    -0.75
     Hy
    -0.71
     Waterfront
    -0.69
     hla
    -0.69
    さき
    -0.68
     wiem
    -0.67
     wied
    -0.65
     berlebihan
    -0.65
    POSITIVE LOGITS
     Spass
    0.71
    ȸ
    0.69
    рис
    0.68
    げた
    0.67
     بار
    0.67
    躬
    0.66
    laki
    0.65
     皮
    0.65
    Uhr
    0.64
    Females
    0.64
    Activations Density 0.056%

    No Known Activations