© 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. 228695
    Prev
    Next
    INDEX
    Explanations

    Russian and English words

    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
    ollen
    0.59
    ow
    0.50
    od
    0.49
    িত্ত
    0.47
    د
    0.47
     on
    0.47
    ij
    0.46
    irc
    0.46
    ?
    0.45
     hydro
    0.45
    POSITIVE LOGITS
     денег
    0.59
     музыки
    0.57
     бонус
    0.55
     остаются
    0.55
     чемпи
    0.55
     книг
    0.54
    (':')[
    0.54
     fatalities
    0.53
     источников
    0.53
     کرا
    0.52
    Activations Density 0.000%

    No Known Activations