© 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. 51944
    Prev
    Next
    INDEX
    Explanations

    perfect finish, plenty warm, had enacted

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

    foreign language 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
     deductions
    0.41
    !!!!!
    0.40
    ไม่ได้
    0.39
     상관
    0.39
    Є
    0.39
     positivity
    0.39
     gifts
    0.39
     losses
    0.38
    Չ
    0.38
    ([
    0.38
    POSITIVE LOGITS
     Telef
    0.52
    クライ
    0.48
     реки
    0.48
     क्रमशः
    0.47
     Nairobi
    0.47
    andı
    0.47
     çeşitli
    0.47
     vardı
    0.46
     தொடங்கியது
    0.46
    ᱕
    0.46
    Activations Density 0.000%

    No Known Activations