© 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. 87036
    Prev
    Next
    INDEX
    Explanations

    page numbers

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

    The neuron detects standalone numeric tokens—page numbers, years, volume and issue numbers, and other citation‐style digits.

    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
    What
    -1.05
     What
    -1.05
     Because
    -1.04
     Since
    -1.01
     творо
    -1.00
    Because
    -0.99
     From
    -0.99
    Although
    -0.97
     How
    -0.96
    According
    -0.96
    POSITIVE LOGITS
    abstract
    1.16
     abstract
    1.11
     Abstract
    1.00
    Abstract
    0.97
     PROFES
    0.96
    )
    0.94
     feuilles
    0.89
    urnal
    0.88
    tique
    0.88
    ändige
    0.88
    Activations Density 0.023%

    No Known Activations