© 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. 15686
    Prev
    Next
    INDEX
    Explanations

    Gemini model name

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

    The neuron strongly fires on the very first token of each new text segment (e.g. section headers or titles).

    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
    http
    0.88
    
    0.84
     http
    0.83
     नष्ट
    0.77
     চিকিত
    0.77
    􀂃
    0.76
     muß
    0.72
     машинасы
    0.70
     xrange
    0.69
    蛋白質
    0.68
    POSITIVE LOGITS
     TikTok
    1.53
    TikTok
    1.41
    🤭
    1.40
     🥰
    1.34
    🫶
    1.34
     impactful
    1.27
     ChatGPT
    1.23
     NFTs
    1.19
    🥰
    1.19
    🫣
    1.17
    Activations Density 0.155%

    No Known Activations