© 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. 171830
    Prev
    Next
    INDEX
    Explanations

    payroll deductions from

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

    Cattle of the Deep

    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
    el
    0.52
    0.50
    ena
    0.49
    y
    0.48
    fen
    0.47
    ner
    0.47
    ums
    0.46
    enas
    0.46
    et
    0.46
    rna
    0.44
    POSITIVE LOGITS
    <unused82>
    0.55
     ヘ
    0.52
    ږئ
    0.52
     tampilan
    0.52
    мещение
    0.51
     DiCaprio
    0.50
     স্ট্যান্ড
    0.49
     ボディ
    0.48
     கோவை
    0.48
     bicicleta
    0.48
    Activations Density 0.000%

    No Known Activations