© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60549
    Prev
    Next
    INDEX
    Explanations

    regex and borough

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

    This neuron fires on single words written in title‐style capitalization—proper nouns or labels such as language names (Bosnian), place names (Borough), or section headings (Regex).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    n
    -3.70
    on
    -3.56
    d
    -3.45
    u
    -3.38
    f
    -3.09
    been
    -2.88
    v
    -2.86
    --
    -2.84
    ăzi
    -2.81
    o
    -2.73
    POSITIVE LOGITS
    ם
    3.27
    ,’
    2.98
     dieną
    2.77
    lossians
    2.67
    ཋ
    2.66
     otras
    2.58
    skor
    2.55
     disposto
    2.55
     angesehen
    2.53
    спомина
    2.53
    Activations Density 0.024%

    No Known Activations