© 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. 84543
    Prev
    Next
    INDEX
    Explanations

    technical programming terms

    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
     on
    -2.16
     in
    -2.05
    :
    -1.88
     by
    -1.88
     -
    -1.83
     all
    -1.78
    >
    -1.77
     from
    -1.76
    at
    -1.73
    u
    -1.68
    POSITIVE LOGITS
     cómodo
    1.91
     nettoy
    1.70
     rafraî
    1.68
     expliquer
    1.67
     envoyer
    1.63
    雠
    1.63
     новая
    1.60
    
    1.56
     diámetro
    1.55
     cómoda
    1.55
    Activations Density 0.069%

    No Known Activations