© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 10603
    Prev
    Next
    INDEX
    Explanations

    affects, due to

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

    This neuron fires on continuous stretches of running prose—that is, it picks up the main body of text (long connected passages) rather than isolated headers or metadata.

    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
     этому
    0.88
     juist
    0.88
     steroids
    0.85
     этот
    0.84
    。
    0.84
     этом
    0.83
     this
    0.82
     corticosteroids
    0.82
     pter
    0.82
     dieses
    0.82
    POSITIVE LOGITS
    ci
    0.73
    又能
    0.70
    ciendo
    0.67
    ларын
    0.67
    lian
    0.65
    愿
    0.64
     توانند
    0.63
    遑
    0.62
     Admittedly
    0.62
    lgende
    0.61
    Activations Density 0.768%

    No Known Activations