© 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. 6596
    Prev
    Next
    INDEX
    Explanations

    i want, you need

    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
     передба
    0.89
     предусмотре
    0.84
    詠
    0.81
     கொள்ள
    0.79
    переди
    0.78
    ેટ
    0.77
     cometido
    0.76
     detección
    0.76
     ად
    0.75
    abah
    0.75
    POSITIVE LOGITS
    oral
    0.87
    封
    0.84
    净
    0.82
    klad
    0.82
    Negative
    0.82
    negative
    0.81
     MULT
    0.81
     Flush
    0.80
     अभिनेता
    0.80
     Multiple
    0.80
    Activations Density 0.105%

    No Known Activations