© 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. 34-GEMMASCOPE-RES-131K
    4. 59298
    Prev
    Next
    INDEX
    Explanations

    code and programming constructs

    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_34/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
     only
    -0.76
     yhte
    -0.69
     prominent
    -0.69
     Olom
    -0.69
    Aerial
    -0.67
     hung
    -0.66
    砾
    -0.65
     سیاه
    -0.65
    sut
    -0.65
     outside
    -0.65
    POSITIVE LOGITS
    TextAlignment
    0.94
     Truss
    0.88
    ſi
    0.87
     Gui
    0.84
     Darum
    0.84
     Японии
    0.84
     ſer
    0.84
     MEASURE
    0.83
     rectangle
    0.83
     Rectangle
    0.83
    Activations Density 0.005%

    No Known Activations