© 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. 240855
    Prev
    Next
    INDEX
    Explanations

    Originality and foreign origins

    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
     zaidi
    0.55
    šli
    0.50
    ---’
    0.48
     istnie
    0.48
    īga
    0.47
    үү
    0.47
    পক্ষের
    0.46
     wɔ
    0.45
     kahit
    0.45
     održ
    0.45
    POSITIVE LOGITS
    ،
    0.58
     Original
    0.52
     ORIGINAL
    0.51
    Original
    0.50
     originals
    0.48
    ，
    0.48
     ARTS
    0.47
    、
    0.46
     strokes
    0.46
    オリジナル
    0.46
    Activations Density 0.002%

    No Known Activations