© 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-IT
    5. 41-GEMMASCOPE-2-RES-65K
    7. 1245
    Prev
    Next
    INDEX
    Explanations

    tiredness

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_41_width_65k_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
    phan
    0.52
    ʋ
    0.52
     बवाल
    0.52
    ̡
    0.50
     Freak
    0.49
     Gould
    0.47
     Ripple
    0.46
    Ƣ
    0.46
    ữu
    0.46
    动手
    0.46
    POSITIVE LOGITS
     fatigue
    3.72
     exhaustion
    3.70
     tiredness
    3.48
     exhausted
    3.45
     tired
    3.39
     fatigued
    3.33
     Fatigue
    3.31
     Exhaust
    3.19
    exhaust
    3.09
    疲
    3.09
    Activations Density 0.240%

    No Known Activations