© 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. 10-GEMMASCOPE-RES-131K
    7. 71775
    Prev
    Next
    INDEX
    Explanations

    major organizations and entities

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

    The neuron is sensitive to words that denote high prominence or top‐tier entities—terms signaling major, leading, or best‐in‐class organizations or categories.

    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
     about
    -1.66
     debes
    -1.55
     podía
    -1.51
     prácticamente
    -1.48
     automáticamente
    -1.43
     iLocal
    -1.41
     frecuentemente
    -1.40
     since
    -1.39
     quizá
    -1.38
     únicamente
    -1.38
    POSITIVE LOGITS
     of
    1.59
     ministres
    1.27
     Eindruck
    1.25
    is
    1.22
    桖
    1.20
     contará
    1.20
    のだろうか
    1.17
    Ꮉ
    1.17
    最新の
    1.17
     hordes
    1.16
    Activations Density 0.119%

    No Known Activations