© 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-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-16K
    7. 8388
    Prev
    Next
    INDEX
    Explanations

    the spruce eats

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_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
     از
    1.01
    يه
    0.94
    зир
    0.93
    לה
    0.84
    rukt
    0.82
    یه
    0.81
    ض
    0.79
    ّه
    0.79
     permanent
    0.79
     rangka
    0.78
    POSITIVE LOGITS
     Marcin
    1.11
     dàng
    1.11
     condimentum
    1.09
     Amerikaanse
    1.08
     methodName
    1.07
    メント
    1.07
    witz
    1.06
     "\\"
    1.06
     tige
    1.03
     Dalmat
    1.02
    Activations Density 0.003%

    No Known Activations