© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 106698
    Prev
    Next
    INDEX
    Explanations

    IDs and table columns

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

    The neuron detects Spanish‐language words or phrases.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     your
    -0.97
     what
    -0.89
     cuida
    -0.88
     konus
    -0.85
    лятор
    -0.77
    柵
    -0.77
    軋
    -0.77
     life
    -0.77
    多彩
    -0.77
    coloring
    -0.76
    POSITIVE LOGITS
    Id
    1.18
     код
    1.16
     ID
    1.15
     cod
    1.11
    コード
    1.08
    ID
    1.06
    编号
    1.04
     Code
    1.03
     نام
    1.00
     id
    1.00
    Activations Density 0.005%

    No Known Activations