© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 118748
    Prev
    Next
    INDEX
    Explanations

    clubs and codes

    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
    ଃ
    -0.78
     SOM
    -0.78
    莛
    -0.77
    stringify
    -0.75
    吉他
    -0.75
    Chars
    -0.74
     ре
    -0.73
    REPO
    -0.73
    chens
    -0.72
    hower
    -0.72
    POSITIVE LOGITS
     clubs
    1.04
     club
    1.03
     Clubs
    0.96
    clubs
    0.96
     code
    0.93
     administration
    0.87
    Clubs
    0.84
    кипедия
    0.83
     Club
    0.82
     codes
    0.82
    Activations Density 0.034%

    No Known Activations