© 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. 16254
    Prev
    Next
    INDEX
    Explanations

    default date exception account

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

    This neuron responds to words that mark location or state (e.g. “in,” “somewhere,” “active”).

    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
    plectic
    0.82
    痳
    0.82
    nV
    0.81
    noy
    0.80
    തും
    0.80
    ्स
    0.78
    奋斗
    0.77
     inlaid
    0.77
    દર્
    0.76
    nol
    0.75
    POSITIVE LOGITS
    -
    0.74
    a
    0.71
    ين
    0.71
    பி
    0.70
    ลิง
    0.70
    ด้
    0.70
    Ɗ
    0.70
     discoveries
    0.69
    либ
    0.69
     community
    0.69
    Activations Density 0.000%

    No Known Activations