© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 105080
    Prev
    Next
    INDEX
    Explanations

    programs, applications, and driving

    np_acts-logits-general · gemini-2.5-flash-lite

    breaks down stereotypes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     boast
    0.48
     Skyscrapers
    0.47
     boasting
    0.47
    蕪
    0.46
     навіть
    0.44
     motivate
    0.44
     reiterate
    0.43
     rations
    0.43
     bragging
    0.41
     rescind
    0.41
    POSITIVE LOGITS
     해
    0.50
     marino
    0.50
     Gynecol
    0.50
    ренного
    0.49
    нять
    0.48
    ЛИ
    0.47
     negativa
    0.46
    haz
    0.46
     invertible
    0.46
    IZED
    0.45
    Activations Density 0.000%

    No Known Activations