© 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. 240093
    Prev
    Next
    INDEX
    Explanations

    foreign unicode characters

    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
    n
    0.52
     tulang
    0.45
     osse
    0.45
     ismer
    0.45
    th
    0.44
     flowed
    0.44
     cookware
    0.44
    ro
    0.44
    w
    0.44
     revolucion
    0.43
    POSITIVE LOGITS
     \
    0.55
    aporation
    0.50
     таблицы
    0.49
     জারি
    0.49
     bố
    0.47
    грамм
    0.45
    瀞
    0.45
    док
    0.44
    かなり
    0.44
     ამ
    0.44
    Activations Density 0.000%

    No Known Activations