© 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. 82282
    Prev
    Next
    INDEX
    Explanations

    variable names like char or num

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ısını
    -0.76
    RAV
    -0.73
     divi
    -0.71
     Landmarks
    -0.71
     Resta
    -0.69
     Victoria
    -0.69
    <0xD8>
    -0.69
    tvguide
    -0.69
    ônes
    -0.68
    Ру
    -0.68
    POSITIVE LOGITS
     char
    1.59
     num
    1.50
    char
    1.43
    num
    1.22
    CHAR
    1.09
     deb
    0.99
    Char
    0.93
    chara
    0.87
     CHAR
    0.87
     شار
    0.87
    Activations Density 0.016%

    No Known Activations