© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 8125
    Prev
    Next
    INDEX
    Explanations

    referencing sections or articles

    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
    There
    -2.05
    Those
    -1.97
    geſ
    -1.84
    4
    -1.79
    Very
    -1.76
    6
    -1.74
     with
    -1.73
    ’
    -1.73
     meski
    -1.69
     kepad
    -1.68
    POSITIVE LOGITS
     dahil
    1.52
    Duh
    1.52
     debacle
    1.43
     of
    1.42
     the
    1.38
     Freien
    1.38
     and
    1.37
     it
    1.37
    iaj
    1.35
     ardından
    1.30
    Activations Density 0.013%

    No Known Activations