© 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. 127826
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ☆、
    -1.75
    arquia
    -1.66
    正義
    -1.66
    Tetapi
    -1.64
    主力
    -1.64
    蹂
    -1.63
    탯
    -1.62
    呦
    -1.60
     strany
    -1.59
     специали
    -1.55
    POSITIVE LOGITS
    甞
    2.02
     castelo
    1.86
     herren
    1.77
     gramas
    1.77
     hina
    1.71
    ໊
    1.71
    mathrm
    1.66
    摁
    1.65
    渽
    1.61
     flamengo
    1.59
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.