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. 788
    Prev
    Next
    INDEX
    Explanations

    detecting numbered sections

    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
    <b>
    1.47
    <h4>
    1.41
    <h3>
    1.36
    <h5>
    1.33
    <h2>
    1.30
    <h1>
    1.19
    <strong>
    1.14
     fai
    1.00
    </blockquote>
    0.98
     think
    0.98
    POSITIVE LOGITS
    IV
    1.47
    İ
    1.29
    NOTE
    1.21
    AND
    1.17
    END
    1.16
    III
    1.14
    ORY
    1.13
    HER
    1.13
    Conclusion
    1.12
    Part
    1.11
    Activations Density 0.566%

    No Known Activations