© 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. 171866
    Prev
    Next
    INDEX
    Explanations

    onsite undercover, donation definition

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

    liability for

    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
    Benzyloxy
    0.48
    َاب
    0.48
    PLACEMENT
    0.48
     INTERACTIONS
    0.47
    BERGER
    0.46
     ABSORBED
    0.46
    룻
    0.46
    ിക്കും
    0.45
    เป็นการ
    0.45
    BEAN
    0.45
    POSITIVE LOGITS
    ade
    0.56
     exemplar
    0.50
     東
    0.50
     é
    0.49
    U
    0.49
    uart
    0.49
     разде
    0.48
    ença
    0.48
     Смо
    0.48
    usive
    0.47
    Activations Density 0.000%

    No Known Activations