© 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. 28006
    Prev
    Next
    INDEX
    Explanations

    cabin charter, no time, harvest, builder, form systems, static Entity, general health, difference

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

    be specific or not 'everyone'

    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
    o
    0.49
    chek
    0.48
    leen
    0.46
     সংশ
    0.44
    quen
    0.44
    氛
    0.44
     Bericht
    0.43
     리뷰
    0.43
    Risk
    0.43
    wort
    0.42
    POSITIVE LOGITS
    ی
    0.62
    езд
    0.51
    ों
    0.50
    に
    0.49
    immunity
    0.47
    HOUR
    0.46
    қты
    0.46
    гана
    0.46
    ytically
    0.46
     वोट
    0.45
    Activations Density 0.000%

    No Known Activations