© 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. 24-GEMMASCOPE-2-RES-16K
    4. 12169
    Prev
    Next
    INDEX
    Explanations

    end of sentence or turn

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

    The neuron strongly activates on numeric tokens and measurements (e.g. digits, numeric ranges, or quantities).

    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
    !!!
    0.65
    !!!");
    0.60
    !!
    0.58
    !(
    0.57
    !!!"
    0.57
    !",
    0.56
    altet
    0.56
     !}\
    0.56
    !”,
    0.56
    ורי
    0.55
    POSITIVE LOGITS
     clerg
    0.63
     immigrant
    0.59
     immigrants
    0.58
    dois
    0.57
     および
    0.57
     poets
    0.55
     identific
    0.55
    および
    0.55
     és
    0.54
    preserved
    0.54
    Activations Density 0.148%

    No Known Activations