© 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. 17-GEMMASCOPE-2-RES-16K
    7. 13496
    Prev
    Next
    INDEX
    Explanations

    Tesseract OCR

    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_17_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
    a
    1.44
    l
    1.39
    ا
    1.35
    ι
    1.23
    ாப்
    1.19
    р
    1.19
    ्या
    1.18
    า
    1.18
    র
    1.17
    া
    1.16
    POSITIVE LOGITS
     Đấy
    1.20
    InChildren
    1.19
    zaXR
    1.19
    ያንዳ
    1.17
    ussed
    1.14
    pcid
    1.13
    ಚ್ಚ
    1.11
    heta
    1.11
    wnież
    1.10
    lesia
    1.09
    Activations Density 0.006%

    No Known Activations