© 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. 128034
    Prev
    Next
    INDEX
    Explanations

    -tone graduated interlocked

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

    connections, information, or causes

    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
    (...)
    0.51
    glycer
    0.46
     occur
    0.45
    एल
    0.45
    submit
    0.45
    ot
    0.44
     coyote
    0.44
    е
    0.44
    posting
    0.44
     diatom
    0.44
    POSITIVE LOGITS
     πραγμα
    0.46
     حاض
    0.46
    帔
    0.45
    期待
    0.43
     আঁচ
    0.43
     نن
    0.43
     रियलिटी
    0.43
     рядом
    0.43
     మరింత
    0.42
    音
    0.42
    Activations Density 0.001%

    No Known Activations