© 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. 10620
    Prev
    Next
    INDEX
    Explanations

    Please, I, you

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

    This neuron fires strongly on the first word or two of each text segment (i.e. sentence/paragraph openings).

    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
    ่วง
    0.56
    硋
    0.56
    惴
    0.52
    they
    0.51
    ttl
    0.51
    ঢ়
    0.51
    걔
    0.51
     ਨਹੀਂ
    0.51
     فقد
    0.50
    它是
    0.50
    POSITIVE LOGITS
    oretically
    1.22
     також
    0.88
    .
    0.82
     Ayrıca
    0.80
    spapers
    0.76
     также
    0.74
    :
    0.74
     tudi
    0.74
    spaper
    0.74
     myös
    0.72
    Activations Density 1.814%

    No Known Activations