© 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. 6788
    Prev
    Next
    INDEX
    Explanations

    pixel dimensions

    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
    llä
    0.79
    theit
    0.77
    CGFloat
    0.77
     expression
    0.76
    ugin
    0.75
    antaranya
    0.72
    avity
    0.71
    )}},
    0.71
    derive
    0.70
     expressions
    0.70
    POSITIVE LOGITS
    pectives
    1.20
    ulfate
    1.03
     Pers
    1.03
    uasion
    1.03
     Persever
    0.98
     Vista
    0.98
    iapan
    0.97
    icaria
    0.96
     rog
    0.95
     persisted
    0.95
    Activations Density 0.044%

    No Known Activations