© 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. 12193
    Prev
    Next
    INDEX
    Explanations

    prior beliefs, probability

    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
    ים
    1.45
    ের
    1.33
    dır
    1.31
    sourced
    1.31
    겪
    1.20
    s
    1.19
    nej
    1.15
    ت
    1.15
    tida
    1.14
    aient
    1.13
    POSITIVE LOGITS
     adhesion
    1.16
     순간
    1.07
     siding
    1.06
     лучше
    1.05
     excluding
    1.03
     dipping
    1.03
     появляется
    1.03
     prze
    1.02
     wd
    1.02
    手
    1.01
    Activations Density 0.002%

    No Known Activations