© 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. 15629
    Prev
    Next
    INDEX
    Explanations

    approximately followed by calculation or context

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

    The neuron fires on floating‐point numeric tokens (decimal numbers).

    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
    weil
    0.79
    ன
    0.74
     demarcation
    0.73
    γραφ
    0.72
    ahar
    0.71
    ρια
    0.70
    સ
    0.70
    ানি
    0.69
    orrow
    0.69
    روز
    0.69
    POSITIVE LOGITS
     ਕੀਤਾ
    0.81
     Instr
    0.72
    競
    0.72
     Independ
    0.71
     Instance
    0.70
    ECS
    0.70
    Competing
    0.68
     Assume
    0.68
     알고
    0.67
    Initializer
    0.67
    Activations Density 0.000%

    No Known Activations