© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 76870
    Prev
    Next
    INDEX
    Explanations

    code syntax and programming terms

    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
    ertale
    -0.89
    (^_^
    -0.75
     esquerda
    -0.73
    subjects
    -0.73
    вная
    -0.72
    Capital
    -0.71
    HON
    -0.71
    mileage
    -0.70
    кать
    -0.70
    ків
    -0.70
    POSITIVE LOGITS
     Sherwood
    0.70
     parade
    0.67
    Weakness
    0.65
    表的
    0.64
     paranoid
    0.63
     suite
    0.63
     Бра
    0.62
    unitas
    0.62
     Suite
    0.61
    飛行
    0.61
    Activations Density 0.055%

    No Known Activations