© 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. 147716
    Prev
    Next
    INDEX
    Explanations

    steps and procedures

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

    danger, adaptation, and IP protection

    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
    p
    0.56
    v
    0.53
    tio
    0.50
    t
    0.50
    daniel
    0.48
    geojson
    0.48
    umble
    0.48
     Zee
    0.47
    gis
    0.47
    g
    0.46
    POSITIVE LOGITS
    措施
    0.46
    环境中
    0.45
    шке
    0.44
    据
    0.42
    ByURL
    0.42
     receptor
    0.42
    酰
    0.41
    Title
    0.41
    製品
    0.41
    Throw
    0.41
    Activations Density 0.000%

    No Known Activations