© 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-262K
    7. 550
    Prev
    Next
    INDEX
    Explanations

    URLs and HTML tags

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

    explanation:

    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_31_width_262k_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
     gluon
    0.37
     vre
    0.36
    </i>
    0.35
     bö
    0.35
     pouls
    0.35
     ما
    0.35
    <start_of_image>
    0.35
     kanamycin
    0.34
    マックス
    0.34
    \":
    0.34
    POSITIVE LOGITS
    <strong>
    0.87
    <em>
    0.63
    <code>
    0.57
    <blockquote>
    0.52
    <h5>
    0.48
    <u>
    0.46
    <h4>
    0.46
    <sub>
    0.44
    <h6>
    0.44
                      
    0.43
    Activations Density 0.005%

    No Known Activations