© 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. 53-GEMMASCOPE-2-RES-262K
    7. 9560
    Prev
    Next
    INDEX
    Explanations

    numbers, money, and dates

    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_53_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
    ২৯
    0.54
    用来
    0.52
    <0xB2>
    0.50
    ❻
    0.46
     ৬
    0.45
    Six
    0.45
    6
    0.43
    六
    0.43
     neun
    0.43
     ২৯
    0.42
    POSITIVE LOGITS
    ৫০
    0.61
     пять
    0.47
     Fifty
    0.45
     fifties
    0.45
    ๕
    0.43
     Этот
    0.43
     ያስ
    0.43
     agosto
    0.43
     fifty
    0.42
    fifty
    0.42
    Activations Density 0.087%

    No Known Activations