© 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. 10338
    Prev
    Next
    INDEX
    Explanations

    Gemini / Gemma model mentions

    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
    ен
    3.09
    k
    2.69
     easel
    2.68
    kere
    2.62
    ة
    2.49
    ే
    2.46
     ong
    2.41
    ת
    2.37
     inference
    2.35
     audition
    2.34
    POSITIVE LOGITS
    м
    2.74
    ${
    2.58
    tedir
    2.52
    +#+#
    2.51
     radionuclides
    2.44
    ্ট
    2.43
    ♦
    2.41
     alters
    2.36
     تعلیم
    2.35
    其他
    2.35
    Activations Density 0.016%

    No Known Activations