© 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. 13-GEMMASCOPE-2-RES-16K
    7. 7007
    Prev
    Next
    INDEX
    Explanations

    Amazon S3, cycle, child, keep

    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_13_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     complete
    1.07
     exactly
    1.05
    য়ের
    1.03
     powdered
    1.03
    ”。
    0.97
    了
    0.96
    .”
    0.95
     anytime
    0.95
     ”.
    0.94
    complete
    0.93
    POSITIVE LOGITS
     interv
    1.05
     depos
    1.02
     marah
    1.02
    hexagon
    1.01
    율
    1.01
     Asalamualaikum
    0.99
    நோய்
    0.97
     localizada
    0.97
     preoccup
    0.95
     preocupación
    0.95
    Activations Density 0.000%

    No Known Activations