© 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. 138407
    Prev
    Next
    INDEX
    Explanations

    foreign languages and specific terms

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

    ethical boundaries

    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
    কলে
    0.43
    命令
    0.43
    ذي
    0.42
    ぶ
    0.41
    حاب
    0.41
    ط
    0.41
    完了
    0.40
    ذهب
    0.40
    叒
    0.39
    بح
    0.39
    POSITIVE LOGITS
     россия
    0.48
    escent
    0.47
     quale
    0.47
    communication
    0.47
     réalis
    0.46
     नाना
    0.46
     wiem
    0.44
     communication
    0.44
     подготов
    0.44
    ėmis
    0.44
    Activations Density 0.000%

    No Known Activations