© 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. 153740
    Prev
    Next
    INDEX
    Explanations

    parts of words

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

    avoiding judgment or rules

    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
    厢
    0.49
    وبا
    0.48
    ड़े
    0.46
    وبت
    0.45
     Ministerial
    0.45
     orchestral
    0.45
     elixir
    0.44
     testigo
    0.43
     Qxb
    0.43
    ότητας
    0.43
    POSITIVE LOGITS
    gn
    0.53
    ᶰ
    0.46
    nta
    0.45
     แยก
    0.44
    NAL
    0.44
    បញ្ចូល
    0.43
    ummy
    0.43
     pregn
    0.42
    分類
    0.42
    unte
    0.42
    Activations Density 0.000%

    No Known Activations