© 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. 12436
    Prev
    Next
    INDEX
    Explanations

    annual seasonal seasonal courts

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

    The neuron fires most strongly on relatively rare or content-rich tokens (i.e. uncommon, informative words or punctuation like question marks).

    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
    𝙮
    1.02
    迪
    0.87
    راہیم
    0.85
     Urinary
    0.85
     Alcoholic
    0.85
    去除
    0.83
     HEALTH
    0.83
    看起来
    0.82
    PROCESSING
    0.82
     SULF
    0.81
    POSITIVE LOGITS
    բ
    0.75
    än
    0.73
    stackpath
    0.69
    жный
    0.69
    iód
    0.68
    ight
    0.67
    ционное
    0.67
    льный
    0.66
     поколения
    0.65
    게
    0.65
    Activations Density 0.000%

    No Known Activations