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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 61107
    Prev
    Next
    INDEX
    Explanations

    stress and fatigue

    np_acts-logits-general · gemini-2.5-flash-lite

    long periods leading to exhaustion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_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
    禁用
    0.43
    弃
    0.43
     ভিক্ষ
    0.41
    খিল
    0.41
    Abandoned
    0.41
    ADA
    0.41
    门口
    0.40
    밉
    0.40
    룻
    0.40
     রুপ
    0.39
    POSITIVE LOGITS
     fatigue
    1.32
     exhaustion
    1.30
    疲れ
    1.29
     tiring
    1.27
     exhausting
    1.27
     Fatigue
    1.22
     fatigued
    1.22
     tiredness
    1.22
    疲
    1.20
     épu
    1.18
    Activations Density 0.139%

    No Known Activations