© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 36477
    Prev
    Next
    INDEX
    Explanations

    dates and life events

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

    available to, evaluated for, calculated in, reveal vulnerabilities

    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
    лянчук
    0.49
    高品質
    0.48
    堰
    0.48
    嗨
    0.47
    Ꮘ
    0.47
    雑
    0.46
    糞
    0.46
    脛
    0.46
    贅
    0.46
    ំនួន
    0.45
    POSITIVE LOGITS
     when
    0.61
     to
    0.51
     final
    0.51
     khi
    0.51
     is
    0.50
     that
    0.49
    when
    0.49
     by
    0.47
     starts
    0.46
     cong
    0.46
    Activations Density 0.000%

    No Known Activations