© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 11121
    Prev
    Next
    INDEX
    Explanations

    The neuron primarily responds to tokens representing numeric values or identifiers (e.g. numbers, metrics, IDs).

    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_31_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
    ToMany
    0.60
     የ
    0.55
    UserId
    0.55
     RBIs
    0.54
     মৃত্যুর
    0.54
    闱
    0.53
     বাজার
    0.52
    資
    0.52
    აწილ
    0.51
     ద్వ
    0.50
    POSITIVE LOGITS
     obiekt
    0.79
     объекта
    0.78
     экземпля
    0.77
     экзем
    0.76
     esemplari
    0.72
     esemplare
    0.72
     chiếc
    0.70
     exemplar
    0.69
    对象
    0.67
     objeto
    0.65
    Activations Density 0.207%

    No Known Activations