© 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. 45906
    Prev
    Next
    INDEX
    Explanations

    P2Pool

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

    styles, lifestyle, chain, relatively, meticulously

    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
    万美元
    0.47
    udge
    0.44
    ćeg
    0.44
    mediate
    0.43
     लिट
    0.43
     सेंटीमीटर
    0.42
    윌
    0.42
     Evidence
    0.42
     रण
    0.41
     कुलपति
    0.41
    POSITIVE LOGITS
     оформления
    0.41
     strtotime
    0.41
    кой
    0.40
     SALES
    0.40
     deviant
    0.40
    nection
    0.39
    🍁
    0.39
    ｝
    0.38
    ೋ
    0.38
     দু
    0.38
    Activations Density 0.000%

    No Known Activations