© 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. 7229
    Prev
    Next
    INDEX
    Explanations

    `cpp` library names

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

    This neuron activates strongly on proper names—especially company, organization, and place 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
    Einstellungen
    0.78
    zechoslovakia
    0.77
     初始化
    0.77
     哦
    0.77
     新品
    0.76
     所以
    0.74
     源
    0.74
    ቖ
    0.74
     τελευτα
    0.73
    altungen
    0.73
    POSITIVE LOGITS
     portion
    0.75
     universe
    0.75
     gamut
    0.74
     family
    0.73
     team
    0.72
     phenomenon
    0.71
     electorate
    0.70
     agenda
    0.70
     system
    0.69
     ordeal
    0.68
    Activations Density 1.203%

    No Known Activations