© 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. 111027
    Prev
    Next
    INDEX
    Explanations

    > ^ == ~> versions

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

    The neuron fires on sequences of digits—especially version‐style numbers—in JSON or code.

    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
     annons
    -1.04
    Most
    -0.94
     will
    -0.94
    ｗｗ
    -0.94
     hundreds
    -0.93
     fifty
    -0.93
    Despite
    -0.91
    🥲
    -0.91
    ▻
    -0.90
     Most
    -0.90
    POSITIVE LOGITS
     себя
    0.94
     версии
    0.91
    >.
    0.91
     první
    0.89
    pared
    0.89
     erforderlich
    0.89
     liberación
    0.89
    깔
    0.87
     envoyer
    0.86
     entsteht
    0.86
    Activations Density 0.018%

    No Known Activations