© 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. 14742
    Prev
    Next
    INDEX
    Explanations

    Youfari And

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

    preoperative sedation

    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
     twofold
    0.49
    elabel
    0.48
     ñ
    0.48
    olist
    0.48
    burgo
    0.47
     agglomer
    0.47
    erjee
    0.46
    año
    0.45
    ibi
    0.44
    тель
    0.44
    POSITIVE LOGITS
    表達
    0.52
    翼
    0.52
    يا
    0.49
     Gaud
    0.49
    丝毫
    0.48
    耽
    0.48
    表达
    0.47
     Drak
    0.46
     wewnętr
    0.45
     terre
    0.44
    Activations Density 0.000%

    No Known Activations