© 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. 34-GEMMASCOPE-RES-131K
    4. 84944
    Prev
    Next
    INDEX
    Explanations

    determiner followed by noun

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

    The main thing this neuron does is detect numeric tokens (i.e. sequences of digits).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    establishment
    -1.05
    rédients
    -1.04
    ਗ਼
    -1.03
    ocirc
    -1.03
    yaret
    -1.02
     детских
    -1.02
     obé
    -1.01
     savag
    -1.01
     لأنه
    -1.01
     tecnologías
    -1.01
    POSITIVE LOGITS
     aforementioned
    1.77
     afore
    1.33
     aforesaid
    1.30
    上述
    1.29
     tersebut
    1.16
     mencionado
    1.12
    :%.
    1.11
    indahan
    1.08
     penyimpanan
    1.06
    t
    1.04
    Activations Density 0.305%

    No Known Activations