© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-16K
    7. 1751
    Prev
    Next
    INDEX
    Explanations

    basketball shooting and scoring

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_16k_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
     Maj
    1.14
     دلو
    1.03
    Hugo
    0.96
     haemat
    0.91
     Moll
    0.88
     mobilisation
    0.88
    changel
    0.88
     T
    0.88
     beet
    0.87
    anges
    0.86
    POSITIVE LOGITS
    🏀
    1.95
     Basketball
    1.92
    asketball
    1.91
    basketball
    1.87
    Basketball
    1.85
    篮球
    1.83
     basketball
    1.82
     Hoop
    1.80
     baloncesto
    1.68
     баскетбол
    1.68
    Activations Density 0.015%

    No Known Activations