© 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. 68596
    Prev
    Next
    INDEX
    Explanations

    special characters and code

    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
     it
    -1.28
     for
    -1.19
    tuvo
    -1.10
     Richard
    -1.10
     In
    -1.08
    结语
    -1.06
     its
    -1.05
    匐
    -1.05
     Scott
    -1.02
     data
    -1.01
    POSITIVE LOGITS
    OBJETIVOS
    1.34
     albeit
    1.28
    albeit
    1.20
    preneurs
    1.17
     magnificent
    1.16
     magnific
    1.16
     affatto
    1.13
    頜
    1.11
    devtool
    1.11
    ciled
    1.11
    Activations Density 0.017%

    No Known Activations