© 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. 200968
    Prev
    Next
    INDEX
    Explanations

    minutes walk

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

    liquids ocean rage case itself

    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
     highly
    0.54
     and
    0.50
    atura
    0.50
     gathering
    0.49
     hanging
    0.49
    で
    0.48
     und
    0.48
     pounding
    0.48
     litter
    0.47
    io
    0.46
    POSITIVE LOGITS
    vať
    0.50
     adaptarse
    0.47
     హైదరాబాద్
    0.47
    байд
    0.46
    getName
    0.46
     вернуться
    0.46
    )->
    0.44
     Bernadette
    0.44
     తెలంగాణ
    0.43
    赫
    0.43
    Activations Density 0.001%

    No Known Activations