© 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. 34-GEMMASCOPE-RES-131K
    7. 30906
    Prev
    Next
    INDEX
    Explanations

    black actors and superheroes

    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_34/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
     speakers
    -0.84
    ليات
    -0.77
     Alabama
    -0.77
    History
    -0.77
     స
    -0.75
    ろう
    -0.75
     History
    -0.74
     խ
    -0.74
    history
    -0.73
     history
    -0.73
    POSITIVE LOGITS
     padx
    0.83
     Khanna
    0.81
    istungen
    0.79
    cn
    0.78
     Rui
    0.77
    IBAN
    0.74
    ktör
    0.72
    styrelsen
    0.70
     Novak
    0.70
     Foxx
    0.69
    Activations Density 0.033%

    No Known Activations