© 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. 146313
    Prev
    Next
    INDEX
    Explanations

    unidentified black, parents always, upholstered inside

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

    background, ethnicity, and role

    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
     calls
    0.42
    l
    0.41
    r
    0.39
     quotes
    0.39
    I
    0.38
    เร
    0.38
     Calls
    0.38
     llamar
    0.38
     It
    0.38
    Phr
    0.38
    POSITIVE LOGITS
    𒆪
    0.57
     spettacolo
    0.52
     कार्यरत
    0.51
     padassa
    0.51
    getvalue
    0.50
     Cheltenham
    0.50
     kecamatan
    0.49
     jede
    0.49
     espectadores
    0.49
     Wikispecies
    0.48
    Activations Density 0.000%

    No Known Activations