© 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. 10489
    Prev
    Next
    INDEX
    Explanations

    current High, equal equals

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

    The neuron fires on qualifier words—adjectives or adverbs that signal comparison, quantity, or temporal relation (e.g. “current,” “multiple,” “different,” “during,” “less”).

    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
    .},
    0.99
     Некоторые
    0.85
     Tatra
    0.82
     которые
    0.82
    ёв
    0.81
     Ov
    0.80
     которым
    0.80
    รูปแบบ
    0.80
     دوم
    0.79
     Рабо
    0.79
    POSITIVE LOGITS
    t
    0.85
     nomm
    0.82
    ${
    0.81
    :
    0.79
    en
    0.78
    שׁ
    0.78
    ます
    0.75
    。
    0.72
     inser
    0.70
    :#
    0.70
    Activations Density 0.000%

    No Known Activations