© 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. 12285
    Prev
    Next
    INDEX
    Explanations

    exact match

    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
    л
    2.90
    크
    2.73
     anionic
    2.64
    но
    2.64
     familiale
    2.62
    ⅾ
    2.56
    نك
    2.50
    ীক
    2.50
    его
    2.45
    ᅨ
    2.45
    POSITIVE LOGITS
    ्स
    3.41
    mselves
    3.40
    𝘁
    3.22
    럼
    3.07
    een
    3.02
    তম
    2.83
    theless
    2.78
    ো
    2.76
    -\{
    2.75
    ્સ
    2.71
    Activations Density 0.009%

    No Known Activations