© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 51516
    Prev
    Next
    INDEX
    Explanations

    football game statistics

    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_65k_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
    㴡
    0.42
    蠱
    0.41
    ទំន
    0.38
    andelier
    0.38
    ร่
    0.37
     scores
    0.37
    Scores
    0.36
    ালা
    0.36
     athleticism
    0.36
    탤
    0.36
    POSITIVE LOGITS
     corner
    0.61
    Corner
    0.57
     Corner
    0.54
    corner
    0.53
     accurate
    0.47
     accuracy
    0.46
     interrupted
    0.46
     corners
    0.46
    corners
    0.46
     clearances
    0.44
    Activations Density 0.009%

    No Known Activations