© 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-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 2435
    Prev
    Next
    INDEX
    Explanations

    HTML, code, and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ा
    1.97
     ín
    1.71
    라도
    1.57
    라
    1.54
    वय
    1.54
    나
    1.52
    יים
    1.48
    তে
    1.48
    в
    1.47
    কর
    1.46
    POSITIVE LOGITS
    tive
    1.79
     bialgebras
    1.69
     Chances
    1.65
     Archivado
    1.63
    fashioned
    1.61
    ાળ
    1.60
    tener
    1.60
     Arten
    1.60
    tad
    1.59
     Daarnaast
    1.58
    Activations Density 0.033%

    No Known Activations