© 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. 16983
    Prev
    Next
    INDEX
    Explanations

    the situated, early

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

    simple everyday causes

    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
     DISCOUNT
    0.54
    がたくさん
    0.54
     duckys
    0.52
    बॉक्स
    0.51
    痔
    0.49
     обши
    0.49
    ्य
    0.48
    涷
    0.48
    ണ്ണ
    0.47
    жем
    0.47
    POSITIVE LOGITS
    m
    0.62
    f
    0.61
    z
    0.61
    g
    0.58
    mountain
    0.56
    p
    0.55
    ster
    0.54
    t
    0.54
    l
    0.54
     can
    0.54
    Activations Density 0.000%

    No Known Activations