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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129622
    Prev
    Next
    INDEX
    Explanations

    not knowing or asking for a clue

    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_10/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
    虯
    -2.63
    ꦁ
    -2.23
    縯
    -2.19
     promesse
    -2.13
     現貨
    -2.09
    廨
    -2.09
    啭
    -2.08
    ᠳ
    -2.08
    忄
    -2.06
     新款
    -2.02
    POSITIVE LOGITS
     of
    2.77
     
    2.66
    .
    2.33
    ?
    2.31
    )
    2.19
     People
    2.05
     heath
    2.03
    に
    2.03
    `
    1.96
    胧
    1.91
    Activations Density 0.003%

    No Known Activations