© 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. 167695
    Prev
    Next
    INDEX
    Explanations

    sports actions and abilities

    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
    遙
    0.39
    ut
    0.39
    Architect
    0.38
     tummy
    0.38
     touch
    0.37
     terapeut
    0.36
    ჰ
    0.36
    ffer
    0.36
     architekt
    0.36
    遥
    0.36
    POSITIVE LOGITS
    Special
    0.52
     SPECIAL
    0.48
     स्पेशल
    0.47
    SPECIAL
    0.46
    Penalty
    0.45
     മത്സര
    0.45
     special
    0.45
     spéciales
    0.45
    Situ
    0.44
     PROTECTION
    0.43
    Activations Density 0.003%

    No Known Activations