© 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. 112312
    Prev
    Next
    INDEX
    Explanations

    the first step

    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
    {
    -1.61
    不可思议
    -1.57
     laatste
    -1.52
     ontvang
    -1.50
    '
    -1.48
    tapete
    -1.45
    いえば
    -1.44
     tierras
    -1.42
    Huile
    -1.42
    ).
    -1.41
    POSITIVE LOGITS
     of
    2.00
    ”
    1.76
     $
    1.70
    G
    1.67
    龊
    1.62
    ног
    1.59
    J
    1.56
    N
    1.55
    ibilité
    1.53
    са
    1.52
    Activations Density 0.009%

    No Known Activations