© 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. 84106
    Prev
    Next
    INDEX
    Explanations

    names authors scientists

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

    author names in academic papers.

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

    This neuron detects numeric tokens—especially page numbers, volume/issue numbers, years, DOIs, and other digits in academic or bibliographic metadata.

    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
     Hvordan
    -1.45
     vakantie
    -1.39
     rurale
    -1.38
     ventanas
    -1.31
    sprzed
    -1.30
     durer
    -1.25
    viembre
    -1.24
     Tienen
    -1.23
     LIBR
    -1.23
     anun
    -1.21
    POSITIVE LOGITS
     for
    1.45
     See
    1.35
     a
    1.34
    —
    1.33
     see
    1.31
    ,
    1.30
     –
    1.30
     similar
    1.24
     actually
    1.22
     Michael
    1.22
    Activations Density 0.007%

    No Known Activations