© 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. 105787
    Prev
    Next
    INDEX
    Explanations

    intensifier followed by description

    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
    hanno
    -1.70
     gewe
    -1.64
    ítmény
    -1.63
     gewi
    -1.62
    ácidos
    -1.55
    ՝
    -1.50
    diez
    -1.50
     saati
    -1.48
     acoso
    -1.45
     Jeden
    -1.44
    POSITIVE LOGITS
    t
    1.77
     if
    1.73
     therefore
    1.48
     
    1.44
     did
    1.39
     التالي
    1.34
    r
    1.34
     folgenden
    1.34
     also
    1.33
     even
    1.31
    Activations Density 0.302%

    No Known Activations