© 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. 175564
    Prev
    Next
    INDEX
    Explanations

    locations and specific entities

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

    monitoring and configuration

    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
    '
    0.48
     gangster
    0.46
    로
    0.45
     crime
    0.44
     droit
    0.44
    crime
    0.43
    장
    0.43
    से
    0.42
     போரா
    0.42
    USE
    0.42
    POSITIVE LOGITS
    нії
    0.51
    творю
    0.51
     بتساوي
    0.48
    туга
    0.48
    쯔
    0.47
    -\{
    0.46
    नून
    0.46
    ्यां
    0.45
    喏
    0.45
     гро
    0.45
    Activations Density 0.000%

    No Known Activations