© 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. 67371
    Prev
    Next
    INDEX
    Explanations

    programming identifiers followed by parentheses

    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
     maniere
    -1.45
     花纹
    -1.35
     inond
    -1.34
     eenig
    -1.34
     robuste
    -1.29
     célè
    -1.27
     investir
    -1.25
    皷
    -1.24
     illimit
    -1.24
    gül
    -1.23
    POSITIVE LOGITS
     with
    1.97
     from
    1.80
     while
    1.68
     P
    1.51
     by
    1.50
     (
    1.40
     also
    1.39
     when
    1.38
     M
    1.37
     two
    1.36
    Activations Density 0.003%

    No Known Activations