© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 31807
    Prev
    Next
    INDEX
    Explanations

    wake locks, keep awake

    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_40_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
     бор
    0.40
     maxHeight
    0.38
    垒
    0.38
     governance
    0.37
     Governance
    0.37
     fro
    0.36
     canopy
    0.36
    岸
    0.36
     collapsible
    0.36
    вля
    0.35
    POSITIVE LOGITS
    Keep
    0.67
    keep
    0.62
     Keep
    0.61
    KEEP
    0.56
    Keeping
    0.55
     keep
    0.54
     kept
    0.54
     Keeping
    0.54
    setKeep
    0.50
     giữ
    0.49
    Activations Density 0.001%

    No Known Activations