© 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. 5572
    Prev
    Next
    INDEX
    Explanations

    phrases following 'year', 'bank', 'smart'

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

    The neuron activates on numeric tokens—especially floating‐point numbers (tokens containing digits and a decimal point).

    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
    吧
    0.73
    othermic
    0.73
    hyst
    0.71
     inférieures
    0.71
     incroy
    0.69
     decirlo
    0.69
     diminuer
    0.68
    Pyro
    0.67
    ात
    0.66
     veux
    0.66
    POSITIVE LOGITS
     แท
    0.89
     Organiz
    0.86
    u
    0.86
     Ohr
    0.84
     oprac
    0.81
     Editing
    0.78
    bies
    0.77
     Эта
    0.76
     Añ
    0.75
     lành
    0.75
    Activations Density 0.000%

    No Known Activations