© 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. 1416
    Prev
    Next
    INDEX
    Explanations

    worsening with or relief by

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

    pain with movement and activity

    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
     রিটার
    0.44
     откло
    0.44
    不对
    0.42
    ेंशियल
    0.42
    োস
    0.42
     نہیں
    0.41
     לא
    0.41
    曏
    0.41
    UNKNOWN
    0.41
    씰
    0.38
    POSITIVE LOGITS
     during
    0.43
     lear
    0.40
     irrespective
    0.40
     භාවිත
    0.39
    ".
    0.39
    .<
    0.38
     after
    0.38
     spezielle
    0.38
    .(
    0.38
    .[
    0.38
    Activations Density 0.001%

    No Known Activations