© 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. 9-GEMMASCOPE-2-RES-262K
    7. 11699
    Prev
    Next
    INDEX
    Explanations

    Chamber of Commerce

    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
    け
    2.50
     ರಲ್ಲಿ
    2.48
    р
    2.43
    蚪
    2.27
    signUp
    2.25
    нути
    2.22
    न्दावन
    2.20
    னர்
    2.19
     czemu
    2.16
    ின்ன
    2.15
    POSITIVE LOGITS
    هي
    3.16
    م
    2.98
    Prosecutors
    2.87
    ^{-}
    2.79
    ه
    2.78
    い
    2.73
    ز
    2.71
    いま
    2.71
    ق
    2.68
    ಾ
    2.65
    Activations Density 0.002%

    No Known Activations