© 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. 160578
    Prev
    Next
    INDEX
    Explanations

    sales, artists, funding, offices

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

    local paths, commands, math

    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
    ב
    0.63
     cupcakes
    0.52
    נ
    0.52
     loaders
    0.51
    declare
    0.50
     style
    0.49
     models
    0.47
    ت
    0.46
    י
    0.46
     infections
    0.44
    POSITIVE LOGITS
     हमें
    0.47
     शेयर
    0.46
     지금
    0.46
    jian
    0.45
     ہمیں
    0.45
    ंपर्यंत
    0.45
    부터
    0.44
    ❘
    0.44
     effettu
    0.44
     우리는
    0.44
    Activations Density 0.000%

    No Known Activations