© 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. 98423
    Prev
    Next
    INDEX
    Explanations

    introductions to topics

    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
     also
    -2.30
     even
    -1.84
     with
    -1.73
     at
    -1.68
     other
    -1.61
     one
    -1.56
     just
    -1.51
     Also
    -1.47
     only
    -1.47
     también
    -1.45
    POSITIVE LOGITS
     célè
    1.83
     éte
    1.50
     irmãos
    1.42
     réinitial
    1.37
     fidé
    1.36
     évé
    1.36
     verhind
    1.34
     aéro
    1.34
     précédents
    1.31
     attente
    1.30
    Activations Density 0.450%

    No Known Activations