© 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. 120362
    Prev
    Next
    INDEX
    Explanations

    technical terms and descriptions

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

    index structure and Japanese verbs

    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
     дзяржа
    0.55
     శ్రీ
    0.50
     bhij
    0.50
     甘
    0.49
     Aal
    0.49
     fundamento
    0.48
     فهو
    0.48
     огне
    0.48
     డ
    0.48
    DefinitionGroup
    0.47
    POSITIVE LOGITS
    ている
    0.55
    取り
    0.47
    向き
    0.45
    یم
    0.44
     hostile
    0.44
    یر
    0.43
    ものを
    0.43
    その
    0.42
    出荷
    0.42
    少し
    0.41
    Activations Density 0.001%

    No Known Activations