© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-65K
    7. 7992
    Prev
    Next
    INDEX
    Explanations

    specifying action or reason

    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_22_width_65k_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
    입니다
    0.94
     Ihres
    0.92
    습니다
    0.91
     Bypass
    0.88
    ﹕
    0.86
    আপনার
    0.85
     Facts
    0.83
    Plugins
    0.82
    您的
    0.82
     Servicios
    0.82
    POSITIVE LOGITS
     specifically
    1.13
     necessarily
    1.13
     unspecified
    1.02
    そもそも
    1.00
     THEN
    0.93
    걍
    0.92
     rather
    0.92
     actually
    0.90
     *
    0.90
     generically
    0.89
    Activations Density 0.253%

    No Known Activations