© 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. 1801
    Prev
    Next
    INDEX
    Explanations

    tensorflow code snippets

    np_acts-logits-general · gemini-2.5-flash-lite

    This neuron detects references to TensorFlow “streaming” metric operations (e.g. streaming_accuracy, streaming_recall, streaming_precision).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     Krank
    -0.79
    력
    -0.77
     πό
    -0.77
    bitos
    -0.77
     Modèle
    -0.75
     mys
    -0.73
     تعریف
    -0.73
    fiore
    -0.72
    SIZES
    -0.71
    Sizes
    -0.71
    POSITIVE LOGITS
     fanfiction
    0.82
    Carpet
    0.81
    íba
    0.79
    ird
    0.78
     Defeat
    0.76
     suelo
    0.75
     amnio
    0.74
     cirka
    0.74
     INSTANCE
    0.73
    Kreuz
    0.73
    Activations Density 0.014%

    No Known Activations