© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 66930
    Prev
    Next
    INDEX
    Explanations

    TODO and FIXME comments and issues

    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
    %;
    -1.95
    }$.
    -1.84
    </i>
    -1.82
     tačiau
    -1.82
     may
    -1.80
     პ
    -1.77
    锇
    -1.72
    合わせた
    -1.70
     -
    -1.66
     we
    -1.64
    POSITIVE LOGITS
    榦
    2.23
     火鍋
    2.06
    an
    2.05
     néhány
    1.98
     收納
    1.98
    〼
    1.93
     rústico
    1.87
     annons
    1.86
    a
    1.82
     放題
    1.81
    Activations Density 0.001%

    No Known Activations