© 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. 5546
    Prev
    Next
    INDEX
    Explanations

    This neuron responds to numerical tokens representing floating-point values.

    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
    ्स
    0.84
    ल
    0.84
    مي
    0.82
    ્સ
    0.80
    ブック
    0.77
    дни
    0.75
    ਨ
    0.75
    зулта
    0.75
    иск
    0.74
     黃
    0.74
    POSITIVE LOGITS
     ie
    0.90
     I
    0.87
    ii
    0.84
    az
    0.83
    set
    0.83
    adapters
    0.82
    ast
    0.80
    android
    0.79
    eth
    0.79
    el
    0.79
    Activations Density 0.000%

    No Known Activations