© 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. 157404
    Prev
    Next
    INDEX
    Explanations

    year, long, or poems

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

    indicator definition syntax

    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
     जरुरत
    0.51
    عام
    0.49
    يش
    0.49
     स्‍
    0.48
    കി
    0.47
    西南
    0.47
    麾
    0.47
    upta
    0.47
     southeast
    0.47
     क्षेत्र
    0.46
    POSITIVE LOGITS
     Dialer
    0.46
    Finally
    0.46
     Díaz
    0.44
    toned
    0.44
    땔
    0.43
    Believe
    0.42
    trou
    0.41
    ﺒ
    0.41
    Jill
    0.40
    Rot
    0.40
    Activations Density 0.000%

    No Known Activations