© 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. 214
    Prev
    Next
    INDEX
    Explanations

    connectors and conjunctions

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

    The neuron activates on numeric tokens—that is, standalone numbers or digit sequences 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_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
    estion
    -1.15
    No
    -1.08
    setcounter
    -1.03
     姆
    -1.02
     first
    -0.99
     voorbeeld
    -0.96
    versiti
    -0.96
     cadeia
    -0.95
     end
    -0.93
    Yeah
    -0.93
    POSITIVE LOGITS
     considérons
    1.14
    Comté
    1.08
     pouvons
    1.00
     soulign
    0.98
     aprecia
    0.96
    咔
    0.93
     voyons
    0.93
     quieran
    0.92
    )
    0.92
     avoient
    0.91
    Activations Density 0.042%

    No Known Activations