© 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. 13582
    Prev
    Next
    INDEX
    Explanations

    Q: or header

    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
     all
    -1.12
     begin
    -1.07
     illustratie
    -1.05
    motors
    -1.05
    بوط
    -1.02
    moreland
    -1.00
     inmig
    -1.00
     uzyskać
    -1.00
    )];
    -1.00
     syke
    -0.97
    POSITIVE LOGITS
     protezione
    1.09
    </em>
    1.02
     attualmente
    0.96
     queste
    0.95
     protože
    0.94
     betreffende
    0.94
     verhe
    0.93
     bụ
    0.93
     essas
    0.91
     bildet
    0.91
    Activations Density 0.001%

    No Known Activations