© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 12193
    Prev
    Next
    INDEX
    Explanations

    mathematical and scientific notation

    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
     makna
    -1.05
    IVENESS
    -1.04
     natale
    -1.01
     hygge
    -1.00
    vereignty
    -0.99
     {},
    
    -0.99
    ыр
    -0.96
    спор
    -0.96
     apartament
    -0.96
    Those
    -0.95
    POSITIVE LOGITS
     here
    1.38
     our
    1.10
     we
    1.09
     comunicaciones
    1.03
     not
    0.93
     wählen
    0.93
     soldadura
    0.91
     this
    0.90
    為に
    0.89
     both
    0.88
    Activations Density 0.006%

    No Known Activations