© 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. 75298
    Prev
    Next
    INDEX
    Explanations

    foreign language words

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

    detection and indicators

    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
     पदाधिकारी
    0.46
     secrétaire
    0.43
    Cad
    0.43
    6
    0.43
    recl
    0.42
    <i>
    0.42
    Y
    0.42
    ften
    0.42
     ll
    0.41
    <0xE2>
    0.41
    POSITIVE LOGITS
    ಚಿ
    0.57
    पहली
    0.51
    गिर
    0.50
    Коммента
    0.50
    পানি
    0.50
    ग्राहक
    0.49
     कैमरा
    0.48
    इंद
    0.48
    پیش
    0.48
    िप्स
    0.48
    Activations Density 0.000%

    No Known Activations