© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118672
    Prev
    Next
    INDEX
    Explanations

    programming tutorials and code

    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
     Reset
    -0.75
     voork
    -0.71
     addUser
    -0.70
     dépla
    -0.70
    lastIndexOf
    -0.69
     Hark
    -0.69
    走る
    -0.69
    Baha
    -0.68
    insert
    -0.68
     バラ
    -0.68
    POSITIVE LOGITS
    tifkan
    0.70
    Pop
    0.70
    Member
    0.69
     zbo
    0.69
    銳
    0.68
    <0x8A>
    0.66
    mitglied
    0.66
    🥥
    0.66
    психо
    0.65
     trunk
    0.64
    Activations Density 0.028%

    No Known Activations