© 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. 36801
    Prev
    Next
    INDEX
    Explanations

    Topical Study, Shipping, responsible

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

    Improving, maintaining, making

    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
    мет
    0.47
    イオン
    0.46
    ника
    0.46
     그런
    0.45
    英國
    0.45
    狹
    0.45
    पत्र
    0.45
    ме
    0.44
    ну
    0.44
     이런
    0.44
    POSITIVE LOGITS
    kev
    0.52
     nad
    0.50
     laag
    0.50
     köl
    0.46
     fö
    0.45
     elucidated
    0.45
     bei
    0.45
    Ma
    0.45
    㕶
    0.44
     feeding
    0.44
    Activations Density 0.000%

    No Known Activations