© 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. 205041
    Prev
    Next
    INDEX
    Explanations

    gallery photos

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

    system integration and control

    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
    0.59
    fore
    0.59
    nal
    0.56
    nless
    0.55
    lo
    0.55
    on
    0.54
    k
    0.54
    omics
    0.53
    for
    0.53
    h
    0.52
    POSITIVE LOGITS
    会の
    0.48
    슛
    0.47
    த்தின்
    0.47
     verdadera
    0.46
    или
    0.46
    ாரா
    0.46
    ங்களின்
    0.43
    تباينه
    0.43
    어야
    0.43
    ந்த
    0.43
    Activations Density 0.001%

    No Known Activations