© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43779
    Prev
    Next
    INDEX
    Explanations

    the following noun

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

    The neuron fires on numeric measurements—i.e. tokens representing numbers (especially decimals or specific quantitative values).

    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
     either
    -1.95
    ↵↵
    -1.63
     entweder
    -1.46
    ↵↵↵
    -1.45
     needed
    -1.44
     Either
    -1.40
     its
    -1.40
     Their
    -1.39
     you
    -1.35
     better
    -1.34
    POSITIVE LOGITS
    ेमाल
    1.53
     kuten
    1.52
    CHREIB
    1.50
     regionales
    1.50
     bereiken
    1.49
    actable
    1.46
     kateg
    1.46
     ideales
    1.43
    sich
    1.42
     bekijken
    1.42
    Activations Density 0.117%

    No Known Activations