© 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. 6680
    Prev
    Next
    INDEX
    Explanations

    side by side, side effects

    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
    тини
    1.16
     পূর্ব
    1.06
    әт
    1.03
    ే
    1.02
    dej
    0.98
     ReactDOM
    0.96
     неде
    0.96
    十大
    0.96
    箇
    0.95
     dư
    0.93
    POSITIVE LOGITS
    kick
    1.46
    bars
    1.09
    burn
    0.92
     hustle
    0.91
    Kick
    0.90
    arm
    0.89
    olateral
    0.87
    cars
    0.86
     streets
    0.84
     opposite
    0.84
    Activations Density 0.064%

    No Known Activations