© 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. 210825
    Prev
    Next
    INDEX
    Explanations

    kumpulan

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

    date formatting and preparation

    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
     ㅅ
    0.47
    URUK
    0.46
    DBG
    0.45
    뇨
    0.44
     وړ
    0.44
    㝒
    0.44
    וו
    0.42
    \(
    0.42
     他
    0.42
     సందర్భ
    0.42
    POSITIVE LOGITS
     концентра
    0.52
    i
    0.49
    arser
    0.44
    iiv
    0.43
    ენტი
    0.43
    ନ
    0.43
     नाहीत
    0.43
    aży
    0.43
     Epidemi
    0.43
    বিষ্য
    0.42
    Activations Density 0.001%

    No Known Activations