© 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. 15940
    Prev
    Next
    INDEX
    Explanations

    acts as an intermediary

    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
     Vä
    0.98
     χρησιμοποι
    0.97
     pr
    0.96
     berbentuk
    0.94
     pos
    0.93
     jotka
    0.91
     /
    0.91
     Jó
    0.91
     wygląd
    0.90
     +
    0.90
    POSITIVE LOGITS
    举
    0.99
    ulate
    0.96
    整个
    0.95
    നിന്ന്
    0.94
     AVER
    0.93
    вому
    0.93
     ইলে
    0.92
    畤
    0.92
    fulness
    0.91
    智
    0.90
    Activations Density 0.012%

    No Known Activations