© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 3118
    Prev
    Next
    INDEX
    Explanations

    ```

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

    The neuron is triggered by numeric expressions, i.e. tokens containing digits or number-like sequences.

    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
     XHTML
    0.73
     elsif
    0.71
    UInt
    0.68
    MBean
    0.66
     Parses
    0.66
    ِلِّ
    0.66
    +#
    0.63
     Annotation
    0.62
     Parsing
    0.61
     Quartz
    0.61
    POSITIVE LOGITS
    🤣🤣
    0.70
     salaire
    0.68
     encarg
    0.68
     encargado
    0.67
    🤑
    0.66
    🤦
    0.65
     ,,
    0.65
     ventaja
    0.64
     koja
    0.64
    kita
    0.64
    Activations Density 0.002%

    No Known Activations