© 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. 31-GEMMASCOPE-2-RES-16K
    4. 537
    Prev
    Next
    INDEX
    Explanations

    books titles and concepts

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

    The neuron activates on numeric expressions—digits, quantities, times, percentages, and other number‐related tokens.

    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_31_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
     
    0.70
     s
    0.56
    ↵
    0.55
     page
    0.54
     data
    0.54
     information
    0.54
    .
    0.53
    -
    0.53
     von
    0.53
     d
    0.52
    POSITIVE LOGITS
    punyai
    0.55
    posaż
    0.54
    ൭
    0.53
    㕮
    0.53
    ementara
    0.52
    isVideoRecording
    0.52
     Сасик
    0.52
     Чем
    0.51
    atthena
    0.51
    agangan
    0.50
    Activations Density 0.170%

    No Known Activations