© 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. 344
    Prev
    Next
    INDEX
    Explanations

    The neuron’s primary function is to pick out numeric or quantitative tokens (e.g. digits, figures, measurements, dates).

    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
    /
    0.35
    。
    0.32
    _
    0.32
    :
    0.32
    ס
    0.31
     and
    0.31
    .
    0.31
            
    0.29
    ().
    0.29
                        
    0.29
    POSITIVE LOGITS
    ख्यात
    0.30
    convén
    0.29
     diesem
    0.28
    fortunately
    0.28
    ravés
    0.28
    więks
    0.27
    न्ही
    0.27
     entanto
    0.27
    ందరు
    0.27
    此同时
    0.26
    Activations Density 18.131%

    No Known Activations