© 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. 236900
    Prev
    Next
    INDEX
    Explanations

    maverick inclinations

    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
    lineWidth
    0.54
    Panel
    0.50
    $
    0.48
    ai
    0.48
    File
    0.46
     Panel
    0.46
    gota
    0.46
     Hilda
    0.46
    γα
    0.45
     transmitters
    0.45
    POSITIVE LOGITS
    呛
    0.45
    న్ని
    0.42
     casas
    0.42
    нков
    0.41
     акции
    0.41
    湡
    0.41
    벌
    0.40
     প্রোগ্র
    0.40
     ගත
    0.40
    শনাল
    0.39
    Activations Density 0.000%

    No Known Activations