© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 13056
    Prev
    Next
    INDEX
    Explanations

    html tag and closing tag

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

    important considerations or notes

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

    HTML closing tags

    np_max-act-logits · claude-4-5-sonnetTriggered by @skarne
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_16k_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
    <h2>
    0.44
    </blockquote>
    0.41
    <0x0C>
    0.41
    浾
    0.41
     convexity
    0.39
    ()\
    0.39
     \\
    0.38
     জ্ব
    0.37
     ока
    0.37
    运气
    0.37
    POSITIVE LOGITS
    </strong>
    0.65
    टरनेट
    0.49
    】：
    0.43
    </b>
    0.42
    ưa
    0.39
    :‏
    0.39
     kiểu
    0.38
    requis
    0.38
     చూప
    0.38
    DefaultFor
    0.37
    Activations Density 0.004%

    No Known Activations