© 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. 34-GEMMASCOPE-RES-131K
    7. 65876
    Prev
    Next
    INDEX
    Explanations

    classifiers 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
    ceas
    -0.79
    我还是
    -0.74
    agus
    -0.73
     überg
    -0.71
    grana
    -0.70
    ismu
    -0.70
    ouldering
    -0.70
     presump
    -0.69
    ைக்
    -0.69
    ɨ
    -0.69
    POSITIVE LOGITS
     classifier
    1.07
     Classifier
    1.03
    Classifier
    1.00
     Lifeline
    0.88
    xor
    0.88
     owned
    0.86
     classifiers
    0.84
     gingival
    0.84
    owned
    0.83
    classifiers
    0.82
    Activations Density 0.005%

    No Known Activations