© 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. 82838
    Prev
    Next
    INDEX
    Explanations

    only true friends

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

    Watching field research unfair

    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
     امرأة
    0.45
     lí
    0.43
     recognisable
    0.43
    Literal
    0.42
     وعند
    0.41
    一个小
    0.41
    矣
    0.41
     ún
    0.41
     resolver
    0.40
     perempt
    0.40
    POSITIVE LOGITS
     nutritious
    0.48
     nutritional
    0.48
     করবে
    0.47
     পাপ
    0.47
    respArray
    0.47
    ayside
    0.46
     মাল
    0.46
    เชิง
    0.46
    ট
    0.46
    nut
    0.46
    Activations Density 0.000%

    No Known Activations