© 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. 86630
    Prev
    Next
    INDEX
    Explanations

    live, unlimited, our, version, degrees, Kendall

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

    regular expression

    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
    และ
    0.57
     و
    0.56
     않았
    0.53
    及び
    0.52
     እና
    0.50
     සහ
    0.50
     ಮತ್ತು
    0.50
     ਅਤੇ
    0.50
     હવે
    0.49
     oude
    0.49
    POSITIVE LOGITS
     binder
    0.48
     prejudicial
    0.42
     regulations
    0.42
     binders
    0.40
    ளோ
    0.40
    ’
    0.40
    Client
    0.39
     seasonings
    0.39
    affected
    0.39
     concerning
    0.39
    Activations Density 0.000%

    No Known Activations