© 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. 90348
    Prev
    Next
    INDEX
    Explanations

    languages and understanding

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

    ** or :** preceding text

    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
     அலெ
    0.48
     क्विक
    0.48
    ogical
    0.46
    ޯ
    0.46
     బ్రిటిష్
    0.46
     handsets
    0.45
     ಸಾಧ್ಯ
    0.45
     ቀላል
    0.45
     रुद्र
    0.45
     usual
    0.44
    POSITIVE LOGITS
    $
    0.52
    +
    0.48
     ve
    0.46
    ))
    0.45
    $.
    0.44
     nast
    0.44
    花费
    0.44
    $)
    0.43
    到
    0.43
    ं
    0.42
    Activations Density 0.001%

    No Known Activations