© 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-3-1B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 5863
    Prev
    Next
    INDEX
    Explanations

    code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_17_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     nă
    0.68
     gef
    0.65
    блон
    0.63
    قر
    0.63
     निगम
    0.63
    ниц
    0.61
     понрави
    0.61
     Lik
    0.61
     ¡
    0.60
    不过
    0.59
    POSITIVE LOGITS
     واذا
    0.73
    Hir
    0.68
     dug
    0.65
    phdr
    0.64
    匕
    0.64
    후
    0.64
    وضع
    0.64
     theory
    0.63
     loan
    0.63
    ,}
    0.63
    Activations Density 0.046%

    No Known Activations