© 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. 16-GEMMASCOPE-2-RES-262K
    7. 27465
    Prev
    Next
    INDEX
    Explanations

    thresholds for decision making

    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_16_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
    وس
    0.69
    ть
    0.64
    }-\
    0.64
    يل
    0.62
     implementations
    0.61
    রা
    0.59
     augmenter
    0.59
    ша
    0.57
     ponctué
    0.57
     এসেছে
    0.57
    POSITIVE LOGITS
     threshold
    1.25
    Threshold
    1.13
    threshold
    1.12
     Threshold
    1.11
     thresholds
    0.89
    阈
    0.84
    THRESHOLD
    0.71
    thresh
    0.70
    AL
    0.68
     ð
    0.68
    Activations Density 0.087%

    No Known Activations