© 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. 128601
    Prev
    Next
    INDEX
    Explanations

    android layout dimensions

    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
     to
    -2.72
     in
    -2.44
     on
    -2.30
     about
    -2.13
     by
    -2.08
     as
    -1.88
     they
    -1.83
     a
    -1.80
     You
    -1.71
     is
    -1.66
    POSITIVE LOGITS
    enseignements
    1.84
     fédé
    1.77
     élar
    1.74
     incendios
    1.72
    Tetapi
    1.70
    鉨
    1.69
     météoro
    1.68
    Namun
    1.64
    Descriere
    1.63
     élastique
    1.63
    Activations Density 0.001%

    No Known Activations