© 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. 10997
    Prev
    Next
    INDEX
    Explanations

    countries, music, TCP, brands

    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
    ਰ
    3.53
    }$
    2.83
    графі
    2.78
    kách
    2.74
    ر
    2.74
    ும்
    2.72
    IVE
    2.69
    ा
    2.68
    yang
    2.61
    erne
    2.61
    POSITIVE LOGITS
    𝗖
    2.85
    ß
    2.78
     forc
    2.69
     ازاي
    2.61
    𝙴
    2.54
     segi
    2.54
    ⅜
    2.51
    wider
    2.51
     Biết
    2.48
     emoji
    2.46
    Activations Density 0.056%

    No Known Activations