© 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. 11209
    Prev
    Next
    INDEX
    Explanations

    common prefixes followed by specific words

    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
    ွက်
    0.33
    ২
    0.33
     执行
    0.32
     хоккей
    0.32
    kében
    0.31
    kommen
    0.31
     আসন
    0.31
    线程
    0.31
    輥
    0.31
     fetched
    0.30
    POSITIVE LOGITS
     mores
    0.42
     or
    0.36
     diverses
    0.34
     calon
    0.34
     Añ
    0.33
     decirlo
    0.33
     eles
    0.32
     Quir
    0.32
     whatnot
    0.32
     forem
    0.32
    Activations Density 0.180%

    No Known Activations