© 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. 248919
    Prev
    Next
    INDEX
    Explanations

    in-stat applicants

    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
    Kappa
    0.52
     câble
    0.50
    賬
    0.44
     sozinho
    0.43
    號
    0.43
    藥
    0.43
     दगडा
    0.42
    농
    0.41
    encerramento
    0.41
    ('{
    0.41
    POSITIVE LOGITS
    getahuan
    0.47
     anlay
    0.47
     dimiliki
    0.46
     இருப்பதால்
    0.45
     Ghaz
    0.45
     karş
    0.45
     RDS
    0.44
     ner
    0.44
     diğer
    0.44
    சார
    0.43
    Activations Density 0.001%

    No Known Activations