© 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. 22-GEMMASCOPE-RES-131K
    7. 67915
    Prev
    Next
    INDEX
    Explanations

    scientific citations and references

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

    numeric page references in academic citations.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron detects numeric strings (volume, page, year, or figure numbers) as they appear in academic 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_22/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
     Have
    -1.37
     that
    -1.34
     having
    -1.34
     of
    -1.31
     have
    -1.30
     from
    -1.26
     specific
    -1.23
    _
    -1.23
     one
    -1.21
     people
    -1.16
    POSITIVE LOGITS
     seksual
    1.17
    obatan
    1.13
    schaft
    1.13
     rigide
    1.12
     花纹
    1.12
     作り方
    1.11
     唯美
    1.09
    Gambar
    1.08
    Elekt
    1.08
    ciendo
    1.07
    Activations Density 0.013%

    No Known Activations