© 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. 10-GEMMASCOPE-RES-131K
    7. 47474
    Prev
    Next
    INDEX
    Explanations

    favorite in, Pacific, conserved H, theatre built, ometer which, medium, management sessions, 3, Goose in, organelles poly, PC boards

    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_10/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
     our
    -1.97
     only
    -1.80
     miljoen
    -1.59
     vacía
    -1.58
     to
    -1.55
     even
    -1.51
     sogar
    -1.40
    mathrm
    -1.37
     devido
    -1.35
     debido
    -1.34
    POSITIVE LOGITS
     avions
    1.49
     ними
    1.44
    They
    1.40
     composants
    1.35
     oreille
    1.33
    彼らは
    1.33
    他們
    1.32
     girasol
    1.31
    THEY
    1.30
     passende
    1.30
    Activations Density 0.200%

    No Known Activations