© 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. 9245
    Prev
    Next
    INDEX
    Explanations

    Dolby Atmos, Vision, HDR

    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
    х
    1.93
    는
    1.91
    \,
    1.78
     않고
    1.59
    зации
    1.56
    ទំនង
    1.56
     фак
    1.55
    𝑔
    1.55
     eventi
    1.53
    만한
    1.53
    POSITIVE LOGITS
    uent
    1.55
    ux
    1.54
    े
    1.53
    e
    1.51
    ذا
    1.51
    as
    1.48
    ীয়
    1.48
    uot
    1.47
     衣装
    1.45
    jest
    1.44
    Activations Density 0.001%

    No Known Activations