© 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. 70896
    Prev
    Next
    INDEX
    Explanations

    vendor software payments

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

    potential outcomes or characteristics

    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
    毯
    0.51
    घाटन
    0.50
    લ્પ
    0.49
    ုပ်တို့
    0.47
    द
    0.46
    لڈ
    0.46
    ৃহে
    0.45
    કિસ્તા
    0.45
     कैलो
    0.45
     інте
    0.45
    POSITIVE LOGITS
    /
    0.53
     Republican
    0.48
    =
    0.47
    _
    0.46
     vendor
    0.45
    M
    0.44
     ling
    0.44
     [
    0.44
     non
    0.44
     Democrat
    0.44
    Activations Density 0.000%

    No Known Activations