© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 15274
    Prev
    Next
    INDEX
    Explanations

    rowing

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_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
     toys
    0.61
     brinqu
    0.59
     spielen
    0.58
     playgrounds
    0.58
     Playground
    0.57
    蒴
    0.57
     playground
    0.55
     spel
    0.55
     giocare
    0.55
     nigra
    0.55
    POSITIVE LOGITS
     rowing
    1.50
     Rowing
    1.45
     rower
    1.38
     oars
    1.38
     row
    1.36
     cox
    1.25
    row
    1.20
    Row
    1.16
    🚣
    1.14
     Row
    1.09
    Activations Density 0.035%

    No Known Activations