© 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-262K
    7. 12123
    Prev
    Next
    INDEX
    Explanations

    ieee.org URLs

    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_262k_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
    न
    1.75
    nosti
    1.74
    upaten
    1.47
    din
    1.43
    ังหวัด
    1.39
    一批
    1.38
    nost
    1.36
    aing
    1.35
    〈
    1.34
    نك
    1.34
    POSITIVE LOGITS
    statusCode
    1.56
    프
    1.45
     работе
    1.37
    লা
    1.30
    Ис
    1.26
    ಿಗೆ
    1.25
     пъ
    1.25
    karte
    1.25
    та
    1.23
    кор
    1.23
    Activations Density 0.000%

    No Known Activations