© 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. 67954
    Prev
    Next
    INDEX
    Explanations

    programming keywords and syntax

    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
     you
    -2.13
     for
    -1.96
     are
    -1.84
     its
    -1.84
     itself
    -1.80
    -
    -1.78
     with
    -1.78
     each
    -1.77
     is
    -1.76
     as
    -1.75
    POSITIVE LOGITS
    蘗
    1.98
     itinéraire
    1.88
     Quels
    1.87
     équilibre
    1.86
    哐
    1.85
     investissement
    1.82
     ſaid
    1.82
     événement
    1.81
     éclairage
    1.73
     procédé
    1.71
    Activations Density 0.060%

    No Known Activations