© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 67306
    Prev
    Next
    INDEX
    Explanations

    how to do

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     but
    -1.12
    ’
    -1.09
     would
    -1.05
    tså
    -1.04
    гы
    -1.02
     ***!
    -1.00
     dalamnya
    -0.99
    telah
    -0.97
     optimieren
    -0.95
     verstor
    -0.95
    POSITIVE LOGITS
    さえ
    1.19
     megfelelő
    1.05
     properly
    1.00
     avulla
    0.98
     doar
    0.98
     Beding
    0.94
     invece
    0.94
    begin
    0.92
     Niem
    0.92
     correctly
    0.91
    Activations Density 0.020%

    No Known Activations