© 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. 72467
    Prev
    Next
    INDEX
    Explanations

    multiplayer modes

    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
     that
    -2.05
     there
    -1.96
     in
    -1.87
     technology
    -1.78
     types
    -1.62
     out
    -1.61
    </em>
    -1.58
     not
    -1.57
     have
    -1.56
     when
    -1.55
    POSITIVE LOGITS
     seulement
    1.91
     internes
    1.81
     appréci
    1.69
     dévelo
    1.67
     baut
    1.66
    ffichage
    1.64
     rapide
    1.64
     frein
    1.63
     เป็น
    1.62
     raiſ
    1.61
    Activations Density 0.016%

    No Known Activations