© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 10194
    Prev
    Next
    INDEX
    Explanations

    It's important, good, about

    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
    ों
    2.44
    tı
    2.43
    可以直接
    2.23
    ిన
    2.23
    hx
    2.22
    sites
    2.21
    s
    2.17
    可以
    2.12
    sı
    2.09
     ഇതു
    2.08
    POSITIVE LOGITS
     raining
    2.63
     dawned
    2.35
     snowing
    2.33
     beho
    2.28
    inerary
    2.14
     Ве
    2.06
    е
    2.00
     conceivable
    2.00
    ва
    1.97
     possível
    1.91
    Activations Density 0.611%

    No Known Activations