© 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. 122598
    Prev
    Next
    INDEX
    Explanations

    information retrieved from databases

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

    handling fulfillment, builder images

    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
    systems
    0.47
     분포
    0.47
     Леони
    0.46
    pel
    0.46
    sockets
    0.46
     졸
    0.45
     symplect
    0.45
    socket
    0.45
     الشكل
    0.45
     특집
    0.44
    POSITIVE LOGITS
     retrieved
    0.48
     retrieves
    0.46
    \%$
    0.46
     |--
    0.46
    ➋
    0.46
     appears
    0.45
     retires
    0.44
     complains
    0.44
    जेस्टिव
    0.43
     pice
    0.43
    Activations Density 0.000%

    No Known Activations