© 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. 10-GEMMASCOPE-RES-131K
    7. 1640
    Prev
    Next
    INDEX
    Explanations

    tensorflow.keras and tfjs

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

    The neuron fires on occurrences of TensorFlow’s “streaming_…” metric function names (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_10/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
     to
    -2.45
     noted
    -1.63
     November
    -1.59
    ła
    -1.59
    '
    -1.44
    \
    -1.41
     extravagant
    -1.38
     –
    -1.38
     gedurende
    -1.36
     February
    -1.35
    POSITIVE LOGITS
     pinggang
    1.71
     wszystkie
    1.66
     diesen
    1.55
     bibir
    1.54
     punggung
    1.52
    you
    1.52
     Imagen
    1.51
    敺
    1.50
    🫘
    1.50
     lengan
    1.50
    Activations Density 0.002%

    No Known Activations