© 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. 75120
    Prev
    Next
    INDEX
    Explanations

    code fragments 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_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
     mierda
    -0.82
     lijkt
    -0.80
    (/*
    -0.78
     zahlreiche
    -0.77
     mensen
    -0.77
    toupper
    -0.72
     serwis
    -0.70
    <!--<
    -0.70
     Système
    -0.70
     ग
    -0.70
    POSITIVE LOGITS
     Each
    0.90
     medži
    0.87
    enska
    0.81
     indivíduo
    0.81
     diph
    0.81
    ISCH
    0.79
     koska
    0.79
    лаго
    0.78
    bosis
    0.77
    writeField
    0.77
    Activations Density 0.006%

    No Known Activations