© 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. 44981
    Prev
    Next
    INDEX
    Explanations

    character names and specific concepts

    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
     craindre
    -1.65
     kampen
    -1.59
     dezelve
    -1.57
     rafraî
    -1.48
     rafra
    -1.45
     remercier
    -1.43
     légèrement
    -1.43
     éclairage
    -1.41
     corriger
    -1.40
     Domínguez
    -1.38
    POSITIVE LOGITS
     from
    2.08
     for
    1.88
    from
    1.66
     at
    1.55
     in
    1.53
     last
    1.47
     are
    1.45
     nine
    1.43
     many
    1.41
    on
    1.38
    Activations Density 0.016%

    No Known Activations