© 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. 13454
    Prev
    Next
    INDEX
    Explanations

    mathematical summation 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
     then
    -1.73
    derdag
    -1.57
     Entste
    -1.51
    がある
    -1.50
    utusan
    -1.49
     dipasang
    -1.48
    siano
    -1.47
    cellence
    -1.44
     Belakang
    -1.44
            
    -1.43
    POSITIVE LOGITS
    Iglesia
    1.71
     där
    1.69
    ity
    1.55
    빌
    1.53
     påver
    1.52
     maniere
    1.50
     mineures
    1.43
     delantero
    1.42
    多么
    1.42
    会出现
    1.41
    Activations Density 0.004%

    No Known Activations