© 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. 6957
    Prev
    Next
    INDEX
    Explanations

    This neuron chiefly detects numeric tokens (especially decimal numbers and numeric citations).

    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
    ]+/
    0.70
     उसको
    0.63
    ]()
    0.63
    fections
    0.60
    vised
    0.60
    :]
    0.59
     %}
    0.59
     potentialities
    0.58
    __':
    0.57
     individuals
    0.55
    POSITIVE LOGITS
    ﻣ
    0.80
    ้ำ
    0.77
    يلي
    0.77
     tasa
    0.72
     మీరు
    0.72
    դ
    0.72
    ย์
    0.71
     Patt
    0.71
     Sprach
    0.70
    ించ
    0.70
    Activations Density 0.000%

    No Known Activations