© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 68387
    Prev
    Next
    INDEX
    Explanations

    names split

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

    This neuron responds to proper nouns, especially personal names.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    توضیحات
    -1.76
    معرفی
    -1.46
    مشخصات
    -1.46
    آموزش
    -1.40
    neden
    -1.30
    を
    -1.29
     ideje
    -1.26
    تاریخ
    -1.26
     halen
    -1.25
    があります
    -1.23
    POSITIVE LOGITS
     who
    1.60
     either
    1.50
     which
    1.38
     everyone
    1.37
     their
    1.37
     what
    1.32
     Шаг
    1.31
     that
    1.30
     this
    1.28
    ure
    1.27
    Activations Density 0.022%

    No Known Activations