© 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. 237096
    Prev
    Next
    INDEX
    Explanations

    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
    Ladies
    0.46
     деньги
    0.46
    CAR
    0.45
    ცა
    0.45
    諄
    0.44
    Money
    0.44
    都有
    0.44
    ع
    0.44
    Fig
    0.43
    Purchase
    0.42
    POSITIVE LOGITS
     başkan
    0.50
     potom
    0.49
     opravdu
    0.49
    děpodob
    0.49
     samband
    0.47
     orche
    0.47
     compagn
    0.47
    يان
    0.46
     gesamten
    0.46
     compañ
    0.46
    Activations Density 0.000%

    No Known Activations