© 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. 6594
    Prev
    Next
    INDEX
    Explanations

    before you commit

    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
    Joshua
    1.05
    David
    0.90
     وزن
    0.89
    boxing
    0.85
    ⇓
    0.84
     ().
    0.84
    Carter
    0.83
     العدد
    0.82
     david
    0.82
    Reynolds
    0.81
    POSITIVE LOGITS
     sende
    1.07
    ിലേക്ക്
    1.05
    ಿನಲ್ಲಿ
    1.03
     noxious
    1.00
     ৯০
    0.99
     condensate
    0.98
     まで
    0.98
     appContext
    0.98
    吐
    0.97
     निर्देश
    0.97
    Activations Density 0.000%

    No Known Activations