© 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. 212541
    Prev
    Next
    INDEX
    Explanations

    rather than

    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
    2
    0.46
     Probably
    0.46
    ಿಕೊಂಡ
    0.46
    зда
    0.46
    ಿಕೊಂಡು
    0.43
    我要
    0.43
    ப்பெ
    0.42
    4
    0.42
    ಿಕೊಳ್ಳ
    0.41
     Charts
    0.41
    POSITIVE LOGITS
    عنی
    0.52
     mouve
    0.50
    dır
    0.50
     chemins
    0.49
     przepis
    0.49
     therapeut
    0.48
     therapeutics
    0.47
     cárc
    0.47
     ły
    0.47
     dormir
    0.46
    Activations Density 0.000%

    No Known Activations