© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 2289
    Prev
    Next
    INDEX
    Explanations

    <b>, <strong>, \textbf, <h1>

    np_acts-logits-general · gemini-2.5-flash-lite

    bolding and mathematical formatting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Архивная
    0.41
    >∕
    0.37
    ूतक
    0.37
    。</
    0.36
    ᓪ
    0.36
    ্যাশ
    0.35
     (€
    0.35
    োজিত
    0.35
    รวจ
    0.35
    িতেছিল
    0.34
    POSITIVE LOGITS
    <b>
    1.25
    <strong>
    1.13
     
    0.69
    textbf
    0.62
     mathbf
    0.54
    boldsymbol
    0.52
    <h4>
    0.47
    <h5>
    0.47
     **
    0.47
    <h1>
    0.46
    Activations Density 0.096%

    No Known Activations