© 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. 34-GEMMASCOPE-RES-131K
    7. 92537
    Prev
    Next
    INDEX
    Explanations

    Email this article

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    ÇO
    -0.76
     pié
    -0.72
    似た
    -0.71
    lüssel
    -0.70
    riendo
    -0.70
     період
    -0.70
    恋愛
    -0.69
    Pontos
    -0.69
     qr
    -0.68
    ßte
    -0.67
    POSITIVE LOGITS
    дика
    0.82
     totality
    0.82
     Gerry
    0.81
    Dequeue
    0.80
     sínt
    0.80
     hygien
    0.78
    ンテ
    0.77
    addCell
    0.77
    wered
    0.77
    Inbox
    0.77
    Activations Density 0.034%

    No Known Activations