© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 211305
    Prev
    Next
    INDEX
    Explanations

    wide receiver catches

    np_acts-logits-general · gemini-2.5-flash-lite

    football passes and catches

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     cardiovascular
    0.47
     atherosclerosis
    0.47
     minerals
    0.46
     aorta
    0.45
    iovascular
    0.45
     キー
    0.45
    銑
    0.44
    дар
    0.44
    鉱
    0.44
    電力
    0.44
    POSITIVE LOGITS
     catch
    0.56
     Catch
    0.54
     Bonding
    0.49
     bonding
    0.45
    χή
    0.43
     Air
    0.43
     Decode
    0.43
     ছাদে
    0.43
     Attic
    0.42
     Giv
    0.42
    Activations Density 0.054%

    No Known Activations