© 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. 10-GEMMASCOPE-RES-131K
    7. 41423
    Prev
    Next
    INDEX
    Explanations

    formatting characters * - _

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

    The neuron is especially sensitive to hyphen or dash punctuation tokens connecting or delimiting words.

    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
    Sejarah
    -2.06
    笮
    -2.06
    Pendidikan
    -2.06
    ꦠ
    -1.92
    Lokasi
    -1.91
    Rumah
    -1.91
     вси
    -1.90
     Ajoutez
    -1.88
    iseen
    -1.88
     counterfeit
    -1.88
    POSITIVE LOGITS
     in
    2.59
     to
    2.17
    ↵
    2.05
    ).
    1.83
     evidenced
    1.82
     a
    1.74
     but
    1.74
     towards
    1.73
     as
    1.67
     they
    1.66
    Activations Density 0.081%

    No Known Activations