© 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. 164553
    Prev
    Next
    INDEX
    Explanations

    University of, MEM, independently owned, grows too, Quakers in

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

    impact on performance or quality

    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
    是
    0.62
     세계
    0.54
    ה
    0.54
    는
    0.53
    ተር
    0.52
    正
    0.52
     아
    0.51
    고
    0.51
     더
    0.51
     코
    0.51
    POSITIVE LOGITS
    xSpeed
    0.50
    sock
    0.46
    addAnimation
    0.45
    کنندگان
    0.45
     ounces
    0.44
    setminus
    0.44
     Bungal
    0.44
     Woodstock
    0.43
    rochemical
    0.43
    INTEGER
    0.43
    Activations Density 0.002%

    No Known Activations