© 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. 119474
    Prev
    Next
    INDEX
    Explanations

    is/was/are/were followed by adjective or past participle

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

    The neuron selectively activates on numeric tokens (especially measurements and decimal numbers) 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
    providedIn
    -1.65
     Μ
    -1.57
     augustus
    -1.50
    createCanvas
    -1.50
    {})
    -1.46
    _
    -1.46
    
    -1.44
     kunst
    -1.42
     maar
    -1.41
     francisco
    -1.39
    POSITIVE LOGITS
     also
    1.71
     debería
    1.56
     keberadaan
    1.55
    Ahol
    1.55
    它们
    1.55
     naszych
    1.53
     dianggap
    1.52
    Organisator
    1.52
     they
    1.49
     consape
    1.48
    Activations Density 0.263%

    No Known Activations