© 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
    5. 7-GEMMASCOPE-2-RES-16K
    7. 2633
    Prev
    Next
    INDEX
    Explanations

    offering help or data at a level

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_7_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     Lobkovic
    2.31
     altın
    2.14
     menyampaikan
    2.12
     Londres
    2.10
     Pengembangan
    2.06
     ünlü
    2.04
     presentó
    2.01
     secretário
    2.00
    ￳
    1.99
     Consultado
    1.98
    POSITIVE LOGITS
     nigg
    1.53
     unnecessary
    1.35
     meaningful
    1.33
     kind
    1.33
     inherent
    1.33
     accruing
    1.32
     unn
    1.32
     incompre
    1.31
     inconsistent
    1.30
     seemingly
    1.30
    Activations Density 1.726%

    No Known Activations