© 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. 202677
    Prev
    Next
    INDEX
    Explanations

    first, anticipate, also

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

    foreign language or specialized terms

    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
     addirittura
    0.48
    泯
    0.48
    뭣
    0.46
     Frankly
    0.45
    ม่
    0.45
    вершен
    0.45
    しかも
    0.45
     Messieurs
    0.44
    mejor
    0.44
     outta
    0.44
    POSITIVE LOGITS
     أيضا
    0.50
    <sup>
    0.49
    *,
    0.48
    ,[
    0.48
     també
    0.46
     außerdem
    0.45
     https
    0.45
     这些
    0.44
    ,*
    0.44
     également
    0.43
    Activations Density 0.026%

    No Known Activations