© 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. 22-GEMMASCOPE-RES-131K
    4. 9645
    Prev
    Next
    INDEX
    Explanations

    verbs indicating state or possession

    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
    ashian
    -1.07
    它们的
    -1.05
    有助于
    -1.05
    すべての
    -1.04
    футбо
    -1.03
    ということです
    -1.01
    kkor
    -1.01
    ța
    -1.00
     которое
    -1.00
     concepción
    -1.00
    POSITIVE LOGITS
     whofe
    1.12
     recently
    1.02
     ebenfalls
    0.99
     tela
    0.99
     his
    0.95
     encantador
    0.95
    酔
    0.94
     occaf
    0.91
     ekonomi
    0.90
     calentamiento
    0.90
    Activations Density 0.024%

    No Known Activations