© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 81405
    Prev
    Next
    INDEX
    Explanations

    citation numbers and details

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

    The neuron specializes in detecting the numeric metadata (years, volume and issue numbers, page ranges, DOIs, etc.) within scholarly reference citations.

    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
     implants
    -0.93
     ส์
    -0.91
     rağmen
    -0.90
    TableField
    -0.88
     eficiencia
    -0.88
     antigos
    -0.85
     eſ
    -0.85
    Garonne
    -0.85
    timents
    -0.84
    ceptive
    -0.84
    POSITIVE LOGITS
     only
    0.86
     out
    0.76
    After
    0.75
     around
    0.72
     with
    0.71
     determining
    0.70
     into
    0.70
     meet
    0.69
    House
    0.68
     “
    0.68
    Activations Density 0.012%

    No Known Activations