© 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. 213
    Prev
    Next
    INDEX
    Explanations

    numbers and punctuation

    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
     to
    -1.58
     declaró
    -1.50
    коля
    -1.48
    6
    -1.46
     confirmó
    -1.45
    кож
    -1.42
     reveló
    -1.41
     but
    -1.41
    之意
    -1.41
     menyadari
    -1.40
    POSITIVE LOGITS
     borracha
    1.83
    我们
    1.66
     ralla
    1.62
     their
    1.57
     two
    1.53
     her
    1.50
     one
    1.49
     him
    1.48
     three
    1.48
     seven
    1.47
    Activations Density 0.008%

    No Known Activations