© 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. 6624
    Prev
    Next
    INDEX
    Explanations

    range

    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
    Hiking
    0.97
    Centre
    0.95
     flats
    0.92
    appartement
    0.89
    ゴー
    0.88
    umela
    0.87
     Hiking
    0.86
     Menon
    0.84
    softmax
    0.84
    Œ
    0.84
    POSITIVE LOGITS
     ബ്ല
    0.86
     aliados
    0.83
     segments
    0.80
     Lindsey
    0.78
     JD
    0.77
    segments
    0.76
    iobium
    0.75
     Hahn
    0.75
     interrupting
    0.75
     Mica
    0.75
    Activations Density 0.081%

    No Known Activations