© 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. 86774
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation followed by specific words

    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
     as
    -2.20
     with
    -2.20
     or
    -2.14
     first
    -2.03
    大家都
    -1.72
    或
    -1.66
     ragazza
    -1.65
     primeras
    -1.63
     restaurantes
    -1.60
     if
    -1.59
    POSITIVE LOGITS
    '
    1.80
    んだから
    1.79
    不由得
    1.70
    がなく
    1.69
     this
    1.63
    立马
    1.62
    这才
    1.56
    が無い
    1.52
     vuonna
    1.50
     therefore
    1.49
    Activations Density 0.102%

    No Known Activations