© 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. 14582
    Prev
    Next
    INDEX
    Explanations

    Southwestern Europe

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

    This neuron fires strongly on the very first word of a sentence or segment (i.e. sentence-initial tokens).

    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
    ”
    0.79
     Inj
    0.76
     “
    0.75
     ['<%=
    0.72
     خرا
    0.70
    ING
    0.69
     littoral
    0.67
     savoir
    0.66
    ht
    0.66
     Natural
    0.66
    POSITIVE LOGITS
     وکړئ
    0.81
    esas
    0.80
    cdot
    0.79
    কার
    0.79
    Cameras
    0.79
    𝗄
    0.79
    cars
    0.78
    𝐰
    0.78
     солне
    0.77
    monotonic
    0.77
    Activations Density 0.000%

    No Known Activations