© 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. 118760
    Prev
    Next
    INDEX
    Explanations

    code punctuation followed by import

    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
     agricoles
    -0.74
     andet
    -0.68
     thermoc
    -0.66
    avana
    -0.66
     Mathematik
    -0.64
    good
    -0.64
    oray
    -0.64
     колон
    -0.64
     Alternate
    -0.63
    atech
    -0.63
    POSITIVE LOGITS
     löyty
    0.71
     шан
    0.70
    ън
    0.69
    dora
    0.68
    Shaun
    0.68
    NFTs
    0.67
     festival
    0.66
    盐
    0.66
     Fudge
    0.66
     دک
    0.66
    Activations Density 0.078%

    No Known Activations