© 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. 12497
    Prev
    Next
    INDEX
    Explanations

    thread safety

    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
    h
    2.47
    ar
    2.34
    اب
    2.32
    coat
    2.30
    ات
    2.30
    ים
    2.21
    élev
    2.18
    ו
    2.06
    luğu
    2.05
    cia
    1.99
    POSITIVE LOGITS
    蛳
    2.50
    ឍ
    2.35
     तरह
    2.29
     Paths
    2.21
    ாக
    2.19
    FileInputExcel
    2.18
     Scriptures
    2.18
     subspaces
    2.16
     antiguos
    2.15
     frighten
    2.14
    Activations Density 0.013%

    No Known Activations