© 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. 32719
    Prev
    Next
    INDEX
    Explanations

    business domain

    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
     subdirectory
    0.44
     sloop
    0.40
    [,-
    0.38
     '),
    0.38
    、​
    0.38
     lineColorSpace
    0.38
    ндо
    0.37
     bá
    0.37
    💬
    0.37
    インターネット
    0.37
    POSITIVE LOGITS
    ເພດ
    0.47
     pepper
    0.39
     feel
    0.38
    pepper
    0.38
    gerät
    0.37
    PSD
    0.37
    CPR
    0.37
    EPS
    0.37
     हस्ताक्षर
    0.37
    feel
    0.37
    Activations Density 0.000%

    No Known Activations