© 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
    3. Gemma-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 8236
    Prev
    Next
    INDEX
    Explanations

    40/41/42 executions

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

    The neuron strongly activates on numeric tokens (and their associated units or place names) that specify distances or measurements to landmarks.

    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
    ską
    0.68
    vVertex
    0.68
    改良
    0.65
    PTMR
    0.62
    であるが
    0.61
    advantages
    0.61
    ग्वि
    0.61
    ዠ
    0.60
    oramic
    0.59
    indrical
    0.59
    POSITIVE LOGITS
    0.73
     actionable
    0.70
     Twitter
    0.66
     Qaeda
    0.66
     TikTok
    0.64
     Salesforce
    0.61
     GitHub
    0.60
     कार्रवाई
    0.59
     three
    0.59
     action
    0.59
    Activations Density 0.002%

    No Known Activations