© 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. 15086
    Prev
    Next
    INDEX
    Explanations

    swing

    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
     TOKEN
    0.62
    TOKEN
    0.57
     category
    0.56
     रिश्ता
    0.56
    垪
    0.55
    adobe
    0.55
     लक्ष्मण
    0.55
    不斷
    0.54
    瑷
    0.54
     চাহিয়া
    0.53
    POSITIVE LOGITS
     swing
    3.86
     Swing
    3.50
    Swing
    3.38
    swing
    3.22
     swings
    3.09
     swinging
    3.08
     swung
    2.92
     Swinging
    2.58
     gear
    1.41
     pendulum
    1.38
    Activations Density 0.044%

    No Known Activations