© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78759
    Prev
    Next
    INDEX
    Explanations

    entity framework, logging, depth

    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
    LError
    -0.79
     acetone
    -0.76
     sesame
    -0.75
    PerSecond
    -0.72
    燃烧
    -0.71
    蛾
    -0.70
    onimo
    -0.68
    Searcher
    -0.68
     سلی
    -0.68
    론
    -0.68
    POSITIVE LOGITS
     deep
    1.24
     shallow
    1.14
    深度
    1.07
     depth
    1.05
     profunda
    1.02
     objects
    1.01
     profundas
    1.00
    deep
    0.97
     recursively
    0.94
     profonde
    0.93
    Activations Density 0.102%

    No Known Activations