© 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. 94637
    Prev
    Next
    INDEX
    Explanations

    foreign languages

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

    multi-word tokens and phrases

    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
    t
    0.53
    uj
    0.52
    n
    0.52
    én
    0.48
    á
    0.48
    más
    0.47
    m
    0.47
    mén
    0.46
    danger
    0.46
    tr
    0.46
    POSITIVE LOGITS
     одном
    0.48
     dielectric
    0.46
     рассказал
    0.45
     রচিত
    0.44
     интервью
    0.44
     interviewee
    0.43
     примере
    0.43
     দেবতা
    0.42
     <$>
    0.41
     حک
    0.41
    Activations Density 0.000%

    No Known Activations