© 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. 10375
    Prev
    Next
    INDEX
    Explanations

    must-have / must see / must hear / must read

    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
    thig
    -2.30
     comanda
    -2.13
     turco
    -2.09
    鋦
    -2.08
     pilote
    -2.03
     evangé
    -1.99
     rusa
    -1.98
     Hinblick
    -1.92
     sélections
    -1.89
     réservoir
    -1.89
    POSITIVE LOGITS
     for
    2.63
     in
    2.55
     also
    2.00
    "
    1.92
     approach
    1.84
     sufri
    1.78
     Five
    1.74
    :
    1.73
     Three
    1.73
    н
    1.70
    Activations Density 0.003%

    No Known Activations