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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-16K
    4. 7543
    Prev
    Next
    INDEX
    Explanations

    regular expression syntax

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_16k_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
     Infine
    0.91
    ῖς
    0.90
    坦克
    0.87
     marking
    0.85
     halftone
    0.84
     dashes
    0.84
     stalemate
    0.83
    ῇ
    0.83
     вигляді
    0.82
    嚎
    0.82
    POSITIVE LOGITS
    ...]
    0.88
    substantial
    0.74
    fires
    0.72
    ου
    0.71
     Tj
    0.71
    zü
    0.71
    two
    0.70
     two
    0.69
     iki
    0.67
    สอง
    0.66
    Activations Density 0.012%

    No Known Activations