© 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. 130658
    Prev
    Next
    INDEX
    Explanations

    #define directive

    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
     Schwierigkeiten
    -0.91
    出错
    -0.89
    igenous
    -0.88
     ILLUSTR
    -0.88
    encana
    -0.88
    paired
    -0.88
     confirmó
    -0.87
    了不少
    -0.87
    denly
    -0.86
     akzep
    -0.86
    POSITIVE LOGITS
    v
    1.06
     ilgi
    1.00
    ocuk
    1.00
    irse
    0.99
     bereits
    0.99
    Rainfall
    0.99
    y
    0.95
     clipping
    0.95
    DETAILS
    0.94
    orgt
    0.93
    Activations Density 0.071%

    No Known Activations