© 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. 90985
    Prev
    Next
    INDEX
    Explanations

    RSVP by calling

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

    list item separators

    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
    Negative Logits
     Qualifications
    0.54
     Qualification
    0.51
    created
    0.48
    る
    0.48
     Created
    0.48
     Describes
    0.48
     Comes
    0.47
    гает
    0.47
    ζ
    0.46
     Explorer
    0.46
    POSITIVE LOGITS
     dönüş
    0.44
    নির্দিষ্ট
    0.43
     سنة
    0.42
     الدولي
    0.41
     කරන්න
    0.41
     logika
    0.41
    Already
    0.40
     немає
    0.40
     sesu
    0.39
     dSample
    0.39
    Activations Density 0.000%

    No Known Activations