© 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. 84142
    Prev
    Next
    INDEX
    Explanations

    numerical digits and symbols

    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
    ּוֹ
    -1.09
    other
    -0.98
     Verenig
    -0.97
     tersangka
    -0.96
     maxime
    -0.96
     schu
    -0.93
    ії
    -0.92
    ᾰ
    -0.90
     other
    -0.90
     vendar
    -0.90
    POSITIVE LOGITS
     whatnot
    1.05
    namn
    1.03
     borboleta
    0.91
    ֺ
    0.91
     lutar
    0.90
    ׇ
    0.90
     इत
    0.88
     chré
    0.87
    klare
    0.87
     cualidades
    0.86
    Activations Density 0.002%

    No Known Activations