Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-16K
    4. 9110
    Prev
    Next
    INDEX
    Explanations

    bowling and games

    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_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
     CpG
    0.81
     Batman
    0.76
     درخت
    0.75
    শংস
    0.74
     Mateo
    0.72
    짖
    0.70
     போர்
    0.70
     विद्रोह
    0.69
    Batman
    0.68
    芨
    0.68
    POSITIVE LOGITS
     bowling
    1.22
     billi
    1.17
    🎱
    1.16
     billiard
    1.06
     Bowling
    0.94
    🎳
    0.92
    Bowling
    0.89
     Pins
    0.87
     bowlers
    0.87
     frit
    0.87
    Activations Density 0.106%

    No Known Activations