© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 5561
    Prev
    Next
    INDEX
    Explanations

    second item in a list

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
    <b>
    3.63
    <h2>
    2.81
    </td>
    2.77
    <h3>
    2.77
    </h3>
    2.42
     }\
    2.17
    </h2>
    2.13
    <h1>
    2.12
    "},{"
    2.09
    贯彻
    2.09
    POSITIVE LOGITS
    <em>
    1.76
    sigh
    1.75
    ANCIS
    1.64
    ît
    1.62
    UPDATE
    1.61
    [...]
    1.59
    ARDO
    1.57
    elden
    1.57
    RELATED
    1.52
    NOTE
    1.51
    Activations Density 0.002%

    No Known Activations