© 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. 89966
    Prev
    Next
    INDEX
    Explanations

    License versions

    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
    vės
    -0.74
     classrooms
    -0.71
    Recognition
    -0.69
    累了
    -0.68
    Mou
    -0.68
    ךְ
    -0.67
    sper
    -0.67
     provider
    -0.66
     City
    -0.66
     оружи
    -0.65
    POSITIVE LOGITS
    XML
    0.94
    ciela
    0.93
    esie
    0.89
     vencedor
    0.88
     XML
    0.85
    ælp
    0.85
    めんな
    0.82
    misión
    0.82
    xmlns
    0.81
    frica
    0.80
    Activations Density 0.003%

    No Known Activations