© 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. 65211
    Prev
    Next
    INDEX
    Explanations

    specific topics or activities

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

    The neuron fires on content-bearing nouns—words that name people, things, events, or concepts.

    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
     all
    -2.44
     even
    -2.23
     their
    -2.11
     every
    -1.97
     first
    -1.92
     only
    -1.81
     both
    -1.70
    </h2>
    -1.68
     each
    -1.63
     к
    -1.61
    POSITIVE LOGITS
    取决
    1.88
     抠
    1.86
     avancer
    1.78
     semblent
    1.73
    specifically
    1.70
    VERY
    1.65
     velmi
    1.60
    perhaps
    1.60
    joueurs
    1.60
    THERE
    1.58
    Activations Density 0.324%

    No Known Activations