© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 71095
    Prev
    Next
    INDEX
    Explanations

    calculation and physics context

    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
    久し
    -1.08
    どうなる
    -1.04
    焼肉
    -1.01
     armazen
    -0.99
    ごちそう
    -0.99
    明日は
    -0.99
     ivo
    -0.98
    hahah
    -0.98
    に入れる
    -0.95
    Niet
    -0.94
    POSITIVE LOGITS
     of
    1.54
     Städten
    1.09
     Staates
    1.05
     متعلقه
    1.04
     which
    1.01
    PropertyGroup
    1.01
    enderal
    0.99
    %"),
    0.99
     There
    0.97
    BIÉN
    0.97
    Activations Density 0.022%

    No Known Activations