© 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
    2. Gemma-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-262K
    4. 11950
    Prev
    Next
    INDEX
    Explanations

    class definitions and object creation

    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
    उनके
    1.63
    playerName
    1.60
     Dois
    1.59
    檚
    1.57
     large
    1.53
    檛
    1.40
    #####
    1.37
     fouled
    1.37
    আমাকে
    1.32
    кой
    1.31
    POSITIVE LOGITS
    اً
    2.57
    서는
    1.96
    ingu
    1.91
    tte
    1.88
    ا
    1.82
    ו
    1.81
    ます
    1.79
    ادة
    1.78
    ième
    1.77
    יות
    1.76
    Activations Density 0.000%

    No Known Activations