© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 1241
    Prev
    Next
    INDEX
    Explanations

    descriptive adjectives

    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
     of
    -2.88
     by
    -2.02
     there
    -1.96
     
    -1.95
    :
    -1.94
     was
    -1.92
     at
    -1.81
     after
    -1.74
     set
    -1.70
     有
    -1.65
    POSITIVE LOGITS
     exigencias
    2.06
     antiguas
    2.06
     sanciones
    1.99
     empezaron
    1.98
     lidé
    1.98
     tomaron
    1.95
     wszyscy
    1.94
     relâche
    1.93
     vieron
    1.91
     Feuchtigkeit
    1.91
    Activations Density 1.459%

    No Known Activations