© 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. 22-GEMMASCOPE-RES-131K
    7. 25560
    Prev
    Next
    INDEX
    Explanations

    user friendly opinions

    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_22/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
     in
    -1.23
     on
    -1.17
     or
    -1.07
     if
    -0.92
     from
    -0.90
    ✿
    -0.90
     JUST
    -0.90
    énieurs
    -0.88
    傳統
    -0.86
    ゲル
    -0.86
    POSITIVE LOGITS
    immortal
    1.05
     travailleurs
    1.05
    rolex
    1.05
    ㌘
    1.04
     apariencia
    1.04
     diſt
    1.03
     obſ
    1.02
    explanatory
    1.01
     salariés
    1.01
    anticipated
    1.01
    Activations Density 0.084%

    No Known Activations