© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 71382
    Prev
    Next
    INDEX
    Explanations

    Checked out, down the, ignore, contained, Chris, Ten Plagues, take drinks, Take Shakespeare

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

    domain names and descriptions

    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
    l
    0.65
    y
    0.59
    s
    0.57
    t
    0.55
    n
    0.54
    x
    0.54
    i
    0.54
    users
    0.49
    v
    0.48
    k
    0.48
    POSITIVE LOGITS
     খাজ
    0.55
     deliberations
    0.50
     preocupaciones
    0.49
     dissemination
    0.49
     disseminating
    0.48
     że
    0.46
     défis
    0.46
     específicamente
    0.46
     प्रीम
    0.46
     أنّ
    0.45
    Activations Density 0.003%

    No Known Activations