© 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. 16160
    Prev
    Next
    INDEX
    Explanations

    asking this question

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

    The neuron fires strongly on multi‐word, title‐style sequences (e.g. book or paper titles) consisting of consecutive capitalized words.

    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
    apopt
    0.81
    coprote
    0.81
    ClickHandler
    0.81
     retort
    0.80
     канторы
    0.79
    ้
    0.79
    tegr
    0.79
    stattung
    0.78
    xido
    0.78
    plitude
    0.78
    POSITIVE LOGITS
     バス
    0.73
    بول
    0.72
     сю
    0.71
    Bathroom
    0.70
    اد
    0.69
    大的
    0.69
    ことで
    0.68
    ファン
    0.66
    世界
    0.65
    毛
    0.63
    Activations Density 0.000%

    No Known Activations