© 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. 10350
    Prev
    Next
    INDEX
    Explanations

    sensitive organ

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

    The neuron flags uncommon or content-rich tokens—especially proper nouns and other rare words.

    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
     внед
    0.77
    AUTOM
    0.75
    Plaintiff
    0.74
    象征
    0.74
    ᆼ
    0.74
    advantage
    0.74
    contribution
    0.74
    verläss
    0.73
    Laur
    0.72
    assert
    0.71
    POSITIVE LOGITS
    mesi
    0.96
     Ayurvedic
    0.96
     ekki
    0.89
     בא
    0.88
     א
    0.86
    ました
    0.85
    tır
    0.84
     ayurved
    0.83
     aloe
    0.81
     Ayurveda
    0.80
    Activations Density 0.001%

    No Known Activations