© 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-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 105045
    Prev
    Next
    INDEX
    Explanations

    names ending in ita

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

    The neuron strongly activates on tokens containing the substring “ita,” especially proper names or words ending in “ita.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     of
    -3.67
    鵟
    -2.88
    鬭
    -2.88
    nt
    -2.36
     setEmail
    -2.27
    欵
    -2.23
    干什么
    -2.22
     estatales
    -2.20
    顚
    -2.19
     übri
    -2.17
    POSITIVE LOGITS
    -
    3.03
    ita
    2.75
     если
    2.63
    ITA
    2.58
    </strong>
    2.23
    ICOLON
    2.23
     It
    2.22
    ский
    2.20
    بدأ
    2.19
     stirred
    2.17
    Activations Density 0.011%

    No Known Activations