© 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. 1249
    Prev
    Next
    INDEX
    Explanations

    of the / of patients

    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
     melakukannya
    -1.55
     rempliss
    -1.54
     cremallera
    -1.48
     secar
    -1.48
    deserved
    -1.46
     delgada
    -1.46
     trasladado
    -1.45
    ୬
    -1.45
    utentic
    -1.45
    
    -1.44
    POSITIVE LOGITS
     is
    2.33
     to
    2.14
     this
    1.95
     at
    1.89
     in
    1.84
     for
    1.81
     was
    1.73
     after
    1.66
     even
    1.53
     on
    1.52
    Activations Density 0.177%

    No Known Activations