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. 9-GEMMASCOPE-2-RES-262K
    4. 7726
    Prev
    Next
    INDEX
    Explanations

    html tags, markdown, or structured text

    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_9_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
     例文帳に追加
    1.69
    <blockquote>
    1.54
    、「
    1.47
     ${({
    1.42
    ³.
    1.41
    。「
    1.37
    Similarly
    1.37
     whatnot
    1.34
    वहीं
    1.32
    ².
    1.31
    POSITIVE LOGITS
    </u>
    2.15
    </strong>
    2.06
    </sup>
    1.88
    </b>
    1.88
    </sub>
    1.79
    </span>
    1.75
    </h2>
    1.61
    </em>
    1.59
    </h3>
    1.52
    </code>
    1.41
    Activations Density 4.061%

    No Known Activations