© 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. 113184
    Prev
    Next
    INDEX
    Explanations

    roles of agents

    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
     in
    -1.70
    葩
    -1.45
     of
    -1.38
     towards
    -1.37
     extremely
    -1.29
    胸口
    -1.27
     about
    -1.27
    .”
    -1.27
     nossas
    -1.23
     renowned
    -1.22
    POSITIVE LOGITS
     enfermo
    1.41
    näm
    1.39
    ėk
    1.39
    آموزش
    1.33
    %;
    1.31
     vehemently
    1.31
    नलोड
    1.31
     variedades
    1.30
    對於
    1.28
     appréci
    1.27
    Activations Density 0.090%

    No Known Activations