© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 12486
    Prev
    Next
    INDEX
    Explanations

    rational numbers and expressions

    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
    Negative Logits
    +\
    1.41
    erah
    1.41
     membut
    1.40
    JScripts
    1.39
    gh
    1.34
     bemo
    1.32
    द
    1.31
    ade
    1.29
     हवाले
    1.29
    ethnic
    1.29
    POSITIVE LOGITS
    𝖊
    1.75
    тли
    1.66
    idł
    1.59
    ת
    1.57
    ي
    1.54
    களில்
    1.54
    办法
    1.49
    nala
    1.49
    íme
    1.49
    л
    1.47
    Activations Density 0.001%

    No Known Activations