© 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. 11144
    Prev
    Next
    INDEX
    Explanations

    positive tone

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

    This neuron fires strongly on the very first significant content word (e.g. section heading or the first non-function word) of a new paragraph or block.

    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
    ٰ
    0.68
     Conversations
    0.67
    ھا
    0.67
    大致
    0.66
    分隔
    0.65
    每次
    0.64
    =============
    0.64
    义务
    0.64
    olischen
    0.64
    手动
    0.64
    POSITIVE LOGITS
     emuls
    0.96
     territo
    0.85
     Роб
    0.85
     conflitto
    0.85
     UAV
    0.84
     ferrite
    0.84
    abhavam
    0.83
    PLL
    0.82
     কক্স
    0.82
     finale
    0.82
    Activations Density 0.000%

    No Known Activations