© 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. 168
    Prev
    Next
    INDEX
    Explanations

    citations and publications

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

    The neuron is primarily detecting the special “beginning of sequence” token.

    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
    
    0.18
    Newswire
    0.17
    
    0.17
    imated
    0.17
    infodisc
    0.17
    administered
    0.17
     regiments
    0.16
    Downloaded
    0.16
    ℗
    0.16
     accession
    0.16
    POSITIVE LOGITS
     Ketika
    0.22
     Jika
    0.21
     Nếu
    0.20
     Khi
    0.20
     Zudem
    0.20
     Beberapa
    0.20
     Mereka
    0.19
     Enquanto
    0.19
     Außerdem
    0.19
     Når
    0.19
    Activations Density 0.459%

    No Known Activations