© 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. 13056
    Prev
    Next
    INDEX
    Explanations

    Person identifiers and names

    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
    感のある
    -0.81
     of
    -0.81
     Inspired
    -0.81
     uses
    -0.80
     Based
    -0.79
     From
    -0.79
     Keep
    -0.77
    angled
    -0.77
    婕
    -0.77
    onekana
    -0.77
    POSITIVE LOGITS
    Figli
    1.05
    IBILITY
    0.98
    dataList
    0.97
    Burial
    0.93
    beutel
    0.89
     maravillosas
    0.88
    مدر
    0.88
    licability
    0.85
    amazon
    0.85
    Priest
    0.85
    Activations Density 0.022%

    No Known Activations