© 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. 191
    Prev
    Next
    INDEX
    Explanations

    places, things, or negation

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

    This neuron activates on named entities—proper nouns like titles, places, brands, and other specific names.

    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
     (
    0.45
     (_
    0.44
     (‘
    0.43
    （
    0.43
     (|
    0.40
     («
    0.40
     ([
    0.39
    သည့်
    0.39
    
    0.38
    --(
    0.38
    POSITIVE LOGITS
    じゃない
    0.79
     nije
    0.78
     değil
    0.75
     नहीं
    0.72
     wasn
    0.68
     não
    0.66
     nicht
    0.64
    തല്ല
    0.64
     není
    0.62
     wasnt
    0.61
    Activations Density 0.000%

    No Known Activations