© 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-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 449
    Prev
    Next
    INDEX
    Explanations

    language identification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_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
     \...
    0.52
    <0x0D>
    0.51
    </strong>
    0.50
    <unused61>
    0.48
     both
    0.47
     继续访问
    0.46
     ...
    0.45
    ＂
    0.45
     remains
    0.45
    `
    0.44
    POSITIVE LOGITS
    Wikimedia
    0.65
    wikidata
    0.62
    Einzelnachweise
    0.60
     బ్రిటిషు
    0.59
     wikipagina
    0.59
    editar
    0.54
     Вики
    0.53
     Wikimedia
    0.52
    <table>
    0.51
     ويكي
    0.50
    Activations Density 0.017%

    No Known Activations