© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 213763
    Prev
    Next
    INDEX
    Explanations

    factual statements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     deacon
    0.38
    代表人
    0.38
     empt
    0.38
    in
    0.38
    deo
    0.37
    娩
    0.37
    理解
    0.36
     lệnh
    0.36
     ගැන
    0.35
    skcipher
    0.35
    POSITIVE LOGITS
     जोखिम
    0.48
    ๚
    0.46
     อาท
    0.43
     такі
    0.43
     такие
    0.41
    държа
    0.40
    өө
    0.40
     precum
    0.39
    เช่น
    0.39
     मुली
    0.39
    Activations Density 0.002%

    No Known Activations