© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 93159
    Prev
    Next
    INDEX
    Explanations

    phrases and services

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

    The neuron activates on numerical tokens (digits or numeric measurements, including integers and decimals).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     nép
    -0.88
     vinilo
    -0.82
     EGG
    -0.78
    gradable
    -0.77
     fungerer
    -0.77
     pageable
    -0.77
     které
    -0.77
    樺
    -0.75
    -0.75
    ictions
    -0.74
    POSITIVE LOGITS
     الحدي
    0.99
     bestimmten
    0.94
    chaun
    0.92
    ensores
    0.90
    HideInInspector
    0.90
     Beberapa
    0.89
     comunale
    0.89
     nowych
    0.88
    estroyer
    0.88
    IGAN
    0.86
    Activations Density 0.120%

    No Known Activations