© 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. 22-GEMMASCOPE-RES-131K
    4. 92946
    Prev
    Next
    INDEX
    Explanations

    and/or conjunctive examples

    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
     célè
    -1.55
     verhind
    -1.52
     siè
    -1.48
     alho
    -1.46
     花纹
    -1.45
     唯美
    -1.41
     disques
    -1.40
    僰
    -1.39
     vernis
    -1.38
     praticamente
    -1.37
    POSITIVE LOGITS
     which
    1.95
     where
    1.94
     etc
    1.86
     but
    1.80
     even
    1.74
     those
    1.74
     others
    1.70
     having
    1.67
     during
    1.61
     does
    1.58
    Activations Density 0.137%

    No Known Activations