© 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. 9732
    Prev
    Next
    INDEX
    Explanations

    http, ㄹ, equal, Milk, T

    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
    ot
    1.21
    ning
    1.19
    pośred
    1.18
    ring
    1.12
    rystall
    1.11
    il
    1.09
    臾
    1.09
    ┬
    1.07
    Certified
    1.07
     বিবেচিত
    1.04
    POSITIVE LOGITS
    ம்
    1.61
    𝐧
    1.55
     인해
    1.50
     eager
    1.49
     adecu
    1.43
     Infinix
    1.41
     oxides
    1.41
    譚
    1.38
     interoper
    1.38
     Alyssa
    1.37
    Activations Density 0.000%

    No Known Activations