© 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. 68379
    Prev
    Next
    INDEX
    Explanations

    starring actors and journals

    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
    ówki
    -0.94
     we
    -0.90
     of
    -0.88
     Præ
    -0.87
    ortheast
    -0.86
    dife
    -0.85
     trabalhar
    -0.84
     Nieren
    -0.83
     Zuh
    -0.83
    matthew
    -0.82
    POSITIVE LOGITS
    icitis
    1.05
     cilt
    1.04
     коже
    1.02
     aventure
    0.98
     horno
    0.98
    Semoga
    0.97
    ofing
    0.95
     foncé
    0.94
     novelas
    0.94
    omeness
    0.92
    Activations Density 0.003%

    No Known Activations