© 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. 19295
    Prev
    Next
    INDEX
    Explanations

    language, protein, proofs, hoard

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

    technical or specialized terminology related to programming, science, and technology.

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

    The neuron is triggered by inflected verb forms (e.g. gerunds in –ing, past participles in –ed, and 3rd-person singular in –s).

    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
     by
    -2.70
     so
    -2.13
     three
    -2.09
     any
    -2.09
     will
    -2.02
     make
    -2.00
     some
    -1.98
     four
    -1.88
     use
    -1.86
     not
    -1.85
    POSITIVE LOGITS
     refroid
    1.77
     花纹
    1.75
     rafraî
    1.66
     accepter
    1.63
     applau
    1.59
     avancer
    1.55
     dette
    1.54
    鮡
    1.52
     varier
    1.52
     diriger
    1.50
    Activations Density 0.165%

    No Known Activations