© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129119
    Prev
    Next
    INDEX
    Explanations

    specific nouns found in factual descriptions

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

    The neuron detects numeric measurements and statistics (numbers, often with decimals) that give quantitative details in the text.

    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
     from
    -1.95
     by
    -1.55
     through
    -1.53
     for
    -1.44
     of
    -1.43
     new
    -1.41
     more
    -1.39
     during
    -1.38
     about
    -1.36
     becomes
    -1.36
    POSITIVE LOGITS
     somente
    1.58
     bedien
    1.45
     bénéficier
    1.44
     lavable
    1.43
     satisfaire
    1.41
     russes
    1.39
    只会
    1.39
     recentes
    1.38
     nimmer
    1.36
     conozco
    1.34
    Activations Density 0.309%

    No Known Activations