© 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-262K
    7. 12341
    Prev
    Next
    INDEX
    Explanations

    reading/pronouncing numbers and notation

    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_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
     ,
    0.78
    ↵↵
    0.77
    ↵
    0.70
    cont
    0.64
    <start_of_image>
    0.64
    Cont
    0.61
    <0xC2>
    0.60
     &
    0.59
     
    0.58
     :
    0.57
    POSITIVE LOGITS
     summation
    0.95
     tatha
    0.94
    .''
    0.94
    igamma
    0.93
    rimidine
    0.92
     Debye
    0.92
     Lipid
    0.91
     Combien
    0.91
     monotonicity
    0.91
    Comma
    0.90
    Activations Density 0.006%

    No Known Activations