© 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-262K
    7. 241409
    Prev
    Next
    INDEX
    Explanations

    endurance stamina

    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_262k_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
    চিন্ত
    0.66
    Tight
    0.60
     حركة
    0.60
    Thought
    0.55
    axx
    0.54
     竹
    0.54
     harek
    0.54
    ভাব
    0.53
    ombies
    0.52
     मुहूर्त
    0.52
    POSITIVE LOGITS
     endurance
    2.23
     Endurance
    1.97
     stamina
    1.88
    耐
    1.34
     Stam
    1.28
     aerobic
    1.28
    耐久
    1.22
     endure
    1.17
     durability
    1.15
     耐
    1.14
    Activations Density 0.034%

    No Known Activations