© 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. 12916
    Prev
    Next
    INDEX
    Explanations

    credit attribution

    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
    —
    -2.81
    l
    -2.77
    y
    -2.44
     affectionately
    -2.33
    ...(
    -2.31
     podendo
    -2.31
    轳
    -2.28
     cujo
    -2.23
     i
    -2.23
     MUCH
    -2.20
    POSITIVE LOGITS
     bianca
    2.31
    儅
    2.25
    Важно
    2.25
    𝙥
    2.23
    ‪.‬‬
    2.23
    Awal
    2.23
     gevoel
    2.23
    warnai
    2.22
    嗞
    2.20
     可以
    2.19
    Activations Density 0.003%

    No Known Activations