© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 9083
    Prev
    Next
    INDEX
    Explanations

    North Carolina, NVIDIA

    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
    ি
    4.02
    =-\
    3.19
    ውነተኛ
    2.87
    jski
    2.80
    ย
    2.74
    =\
    2.68
    <0xAB>
    2.67
    јединачна
    2.63
    ...+
    2.61
    ksh
    2.61
    POSITIVE LOGITS
    ان
    3.57
    𝘳
    3.16
    ड
    3.10
    an
    3.08
    withstanding
    3.05
    ности
    2.99
    𝘧
    2.95
    ar
    2.94
    𝘢
    2.94
    ান
    2.91
    Activations Density 0.067%

    No Known Activations