© 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. 6753
    Prev
    Next
    INDEX
    Explanations

    ai assistant

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

    The main thing this neuron does is spot references to chemical gases (like carbon monoxide, methane, propane) and related hazard terms.

    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
    doesn
    0.86
    there
    0.75
    achlor
    0.74
     ด่า
    0.72
    ه‌ی
    0.71
    ன
    0.71
     แนว
    0.71
     popolare
    0.70
    ificato
    0.70
     становништво
    0.69
    POSITIVE LOGITS
    ي
    0.86
     Nuestro
    0.81
     Magellan
    0.78
     expedite
    0.75
     Shanghai
    0.75
     Ghana
    0.73
     êtes
    0.73
     handlebars
    0.73
    க்கொண்டு
    0.71
     Melanes
    0.70
    Activations Density 0.000%

    No Known Activations