© 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. 28629
    Prev
    Next
    INDEX
    Explanations

    linear algebra and grades

    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
     கந்தகோ
    0.44
    線の
    0.44
    щенко
    0.44
     माँग
    0.42
     вимо
    0.41
    隀
    0.40
     مود
    0.40
     ውጤ
    0.40
    เฟ
    0.39
     roda
    0.39
    POSITIVE LOGITS
    <td>
    0.50
    (*)
    0.47
    <i>
    0.45
    *
    0.45
    NCC
    0.44
    (
    0.43
    粗
    0.43
    时间
    0.41
     তৈ
    0.40
    toLocale
    0.40
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.