© 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. 8796
    Prev
    Next
    INDEX
    Explanations

    palm rejection, Snake and, colleges and

    np_acts-logits-general · gemini-2.5-flash-lite

    The main thing this neuron does is detect numeric tokens containing decimal points.

    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
     Lobkowicz
    0.93
    д
    0.91
    掟
    0.84
     Νο
    0.82
     Ком
    0.81
    ïque
    0.79
     νο
    0.79
    льному
    0.75
     IMMEDIATE
    0.74
     PROBLEMS
    0.73
    POSITIVE LOGITS
    en
    0.85
    nios
    0.82
    Eq
    0.80
    a
    0.78
    ع
    0.76
     heath
    0.72
    aus
    0.71
    裁剪
    0.70
    他和
    0.70
     वरि
    0.70
    Activations Density 0.001%

    No Known Activations