© 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. 159397
    Prev
    Next
    INDEX
    Explanations

    intercession, certifies, fields, fat, candles, clean, twice

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

    definitions and lists

    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
    غ
    0.66
     preuve
    0.53
    ீர்
    0.47
    た
    0.47
    DEPLOY
    0.46
    ен
    0.46
     догово
    0.46
     actionMode
    0.46
    бран
    0.46
    濯
    0.45
    POSITIVE LOGITS
    winners
    0.55
    ance
    0.54
    mass
    0.53
    ley
    0.53
    an
    0.52
    meter
    0.51
    ag
    0.51
    vals
    0.50
    atura
    0.49
    wards
    0.48
    Activations Density 0.000%

    No Known Activations