© 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. 5895
    Prev
    Next
    INDEX
    Explanations

    conditional execution

    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
    @
    0.88
    loving
    0.74
    aime
    0.69
    \'{
    0.65
    letter
    0.65
    \@
    0.65
    အတွ
    0.64
     disple
    0.64
    likle
    0.64
     epistle
    0.63
    POSITIVE LOGITS
    িনা
    0.77
     simplement
    0.74
    かも
    0.74
     শুধু
    0.72
    羸
    0.71
     கூட
    0.69
     digoxin
    0.69
     naprawdę
    0.69
    rootScope
    0.67
     Gradually
    0.67
    Activations Density 0.025%

    No Known Activations