© 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. 6994
    Prev
    Next
    INDEX
    Explanations

    page and volume numbers

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

    The neuron strongly activates on multi‐digit numeric tokens (page numbers, volume/issue numbers, years, etc.) in bibliographic or citation contexts.

    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
     sintomi
    -0.93
    ارس
    -0.93
     beliebtesten
    -0.86
    apiKey
    -0.85
     Shortly
    -0.85
    romolecules
    -0.84
     During
    -0.84
    apikey
    -0.83
    ffeine
    -0.82
     Issus
    -0.81
    POSITIVE LOGITS
    subtract
    0.93
    Incident
    0.92
     complexe
    0.91
    incident
    0.90
    なん
    0.89
     blant
    0.88
    ⭐⭐⭐⭐
    0.88
    nes
    0.84
    come
    0.84
    𝑛
    0.84
    Activations Density 0.004%

    No Known Activations