© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 10272
    Prev
    Next
    INDEX
    Explanations

    fatigue

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

    The neuron detects expressions of extended time or duration, especially tokens like “long,” “longer,” or similar comparative time‐length words.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_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
     видимо
    0.58
     '';
    0.56
     borderRadius
    0.54
     تقویت
    0.53
    $('#
    0.50
     наве
    0.49
     فائدہ
    0.49
    ﹉
    0.49
     calves
    0.48
     adik
    0.48
    POSITIVE LOGITS
     fatigued
    0.68
     exhausted
    0.60
     Fatigue
    0.60
     Gletscher
    0.60
    exhaust
    0.60
     weary
    0.59
     Tired
    0.58
     Exhaust
    0.58
    miers
    0.57
     tiredness
    0.55
    Activations Density 0.014%

    No Known Activations