© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 320
    Prev
    Next
    INDEX
    Explanations

    The neuron fires on standalone numeric tokens (sequences of digits).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     philanthrop
    0.24
    infodisc
    0.23
    மிகு
    0.22
     multitudes
    0.22
     imbib
    0.22
     swiftly
    0.21
     Erika
    0.21
    
    0.20
    হই
    0.20
     demoral
    0.20
    POSITIVE LOGITS
    0
    0.29
    2
    0.25
    ️⃣
    0.25
    1
    0.24
    9
    0.24
    5
    0.23
    <0x8C>
    0.23
    +
    0.23
    X
    0.22
    P
    0.21
    Activations Density 1.415%

    No Known Activations