Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 36983
    Prev
    Next
    INDEX
    Explanations

    collapsing and exhausted states

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_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
     inap
    0.41
    铧
    0.40
    🐥
    0.40
    準備
    0.39
     arbe
    0.39
     बढ़ता
    0.39
    鏗
    0.38
     Vẽ
    0.37
    ACTIVE
    0.36
     તૈય
    0.36
    POSITIVE LOGITS
     exhausted
    0.82
     recover
    0.70
     exhaustion
    0.70
     aftermath
    0.69
     recovery
    0.68
     recovering
    0.65
     exhausting
    0.62
     survivors
    0.61
     recoveries
    0.61
     recovers
    0.60
    Activations Density 0.032%

    No Known Activations