© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 8583
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on numeric tokens with decimal points (i.e. floating-point numbers).

    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
     educativos
    0.98
     críticos
    0.86
     existir
    0.85
     baños
    0.85
    གས་
    0.84
    𒅎
    0.83
     существо
    0.80
     empe
    0.79
     potenciales
    0.78
    ўным
    0.78
    POSITIVE LOGITS
    )&&
    0.79
    are
    0.77
    ete
    0.73
    TO
    0.73
    ').
    0.72
    ">'+
    0.68
    j
    0.68
    if
    0.64
    Group
    0.64
    да
    0.63
    Activations Density 0.001%

    No Known Activations