© 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. 136699
    Prev
    Next
    INDEX
    Explanations

    other people, Ichiran, hot pot

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

    specialized medical terms

    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
    ні
    0.46
     avait
    0.44
    英語
    0.43
    razine
    0.43
    гі
    0.43
     best
    0.43
    ogn
    0.43
    赵
    0.43
    пі
    0.42
    atform
    0.42
    POSITIVE LOGITS
     Bóng
    0.53
     rupani
    0.47
     પાર્
    0.46
     içine
    0.46
     Editar
    0.45
     drugih
    0.44
     clap
    0.44
     poema
    0.44
     potrà
    0.43
     regalías
    0.43
    Activations Density 0.001%

    No Known Activations