© 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. 5415
    Prev
    Next
    INDEX
    Explanations

    concerned with

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

    The neuron is looking for longer, uncommon content words—especially those with multiple syllables.

    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
    蟳
    0.82
    ڦ
    0.81
    ใหญ่
    0.79
    Ћ
    0.79
    giphy
    0.77
    Airbnb
    0.77
    Př
    0.75
    预览
    0.75
    ٱ
    0.75
    openjdk
    0.74
    POSITIVE LOGITS
     (
    0.93
     creatures
    0.92
     ముఖ్య
    0.89
     items
    0.89
     objects
    0.84
     entities
    0.84
     atoms
    0.83
     processors
    0.83
     activities
    0.82
     factors
    0.81
    Activations Density 0.969%

    No Known Activations