© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-65K
    7. 8007
    Prev
    Next
    INDEX
    Explanations

    throwing action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_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
     sirf
    0.96
     наличие
    0.94
     있게
    0.94
     त्वचा
    0.90
     Höhen
    0.90
    errated
    0.88
    transferases
    0.87
    ৫
    0.87
    cję
    0.86
    Electricity
    0.86
    POSITIVE LOGITS
     throwing
    1.63
     throw
    1.58
     Throw
    1.56
     threw
    1.54
     throws
    1.52
    Throw
    1.50
     overboard
    1.48
     tossed
    1.45
    掷
    1.45
     thrown
    1.44
    Activations Density 0.042%

    No Known Activations