© 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. 68302
    Prev
    Next
    INDEX
    Explanations

    technical questions and descriptions

    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
    -2.58
     теми
    -2.55
     Obviously
    -2.38
     However
    -2.34
    ↵
    -2.34
     ponen
    -2.34
    既然
    -2.33
    mbda
    -2.30
     Since
    -2.27
     That
    -2.25
    POSITIVE LOGITS
    螄
    3.77
    虓
    3.00
    蟥
    2.44
    {
    2.38
     ..........
    2.38
    ungalows
    2.38
     .........
    2.36
     Konkur
    2.33
    凩
    2.33
     ..............
    2.31
    Activations Density 0.000%

    No Known Activations