© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 4240
    Prev
    Next
    INDEX
    Explanations

    or / and

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

    This neuron responds to “/” tokens used as separators in numeric expressions (dates, times, fractions, etc.).

    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
    Warum
    0.34
    ajā
    0.32
    う
    0.31
    She
    0.31
    Би
    0.31
     około
    0.31
    Ռ
    0.31
    Otra
    0.30
     też
    0.30
     również
    0.30
    POSITIVE LOGITS
    /');
    0.39
     combinations
    0.33
     иных
    0.33
    /");
    0.33
    ில
    0.33
     trustworthy
    0.32
     imperfections
    0.31
     omissions
    0.31
     정보를
    0.31
     impairments
    0.31
    Activations Density 0.195%

    No Known Activations