© 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. 22-GEMMASCOPE-RES-131K
    7. 130749
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and expressions

    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
     naer
    -1.30
     annons
    -1.22
     eſt
    -1.17
    
    -1.17
     Garantía
    -1.16
    äste
    -1.16
     utiliser
    -1.15
    鸬
    -1.15
     çay
    -1.13
    damit
    -1.13
    POSITIVE LOGITS
     what
    1.25
     (
    1.10
     took
    1.07
     with
    1.06
     take
    0.97
     want
    0.97
     $(
    0.97
     important
    0.93
     между
    0.93
    四年
    0.93
    Activations Density 0.005%

    No Known Activations