© 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. 133969
    Prev
    Next
    INDEX
    Explanations

    servers, wheels, card, area

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

    what is

    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
    },\
    0.50
     فيها
    0.48
    ಗ
    0.47
     مخت
    0.47
    ель
    0.47
     вирі
    0.47
     فيه
    0.46
     ferm
    0.45
     وط
    0.45
     दिलच
    0.44
    POSITIVE LOGITS
    “
    0.52
     Eugen
    0.46
     semicolon
    0.45
     Match
    0.45
    “(
    0.45
     Connecting
    0.45
     RN
    0.44
     Lect
    0.44
     Connectivity
    0.44
     Hitchcock
    0.44
    Activations Density 0.002%

    No Known Activations