© 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. 38921
    Prev
    Next
    INDEX
    Explanations

    Q: or FAQ

    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
     then
    -1.49
    簠
    -1.45
    ドール
    -1.43
     it
    -1.41
    ⅈ
    -1.41
     '
    -1.38
     by
    -1.38
     heutige
    -1.38
     damal
    -1.37
     現在
    -1.36
    POSITIVE LOGITS
     tega
    1.43
    <bos>
    1.42
    2
    1.41
    雳
    1.36
     sesi
    1.36
     kedi
    1.34
     kredi
    1.34
    signable
    1.31
     with
    1.30
    ଢ
    1.30
    Activations Density 0.042%

    No Known Activations