© 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. 34985
    Prev
    Next
    INDEX
    Explanations

    control limit

    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
    cules
    0.39
    vos
    0.39
     wastage
    0.38
    nus
    0.37
    +|\
    0.35
    }}^{*}\
    0.35
    ális
    0.34
     beet
    0.34
     eser
    0.34
     dif
    0.34
    POSITIVE LOGITS
     развития
    0.42
     збіль
    0.42
     подписа
    0.41
     oranı
    0.40
    iceps
    0.40
     разгово
    0.39
     Accesat
    0.39
    赁
    0.38
    到达
    0.37
    Increased
    0.37
    Activations Density 0.000%

    No Known Activations