© 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. 22-GEMMASCOPE-2-RES-16K
    7. 6740
    Prev
    Next
    INDEX
    Explanations

    refusing harmful requests

    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_22_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
     Gord
    1.41
     Bourg
    1.30
     Cartier
    1.28
     Fiona
    1.23
    混沌
    1.21
     Lac
    1.19
     Gret
    1.18
     Ř
    1.17
     Aoki
    1.15
     Domino
    1.15
    POSITIVE LOGITS
     Samuels
    1.42
     Sample
    1.19
     Samu
    1.18
    Sample
    1.13
     sample
    1.11
    sample
    1.11
     SAM
    1.11
    Handle
    1.08
    Manu
    1.08
     Manu
    1.05
    Activations Density 0.679%

    No Known Activations