© 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. 73256
    Prev
    Next
    INDEX
    Explanations

    programmatically

    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_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
    Setelah
    -3.84
    琹
    -3.20
     When
    -2.94
    чка
    -2.89
    𖣘
    -2.86
     pembun
    -2.81
    Beberapa
    -2.72
    鯪
    -2.66
     With
    -2.64
    Sebelum
    -2.61
    POSITIVE LOGITS
     to
    3.00
    '
    2.94
    萑
    2.92
    迓
    2.84
    汭
    2.75
    :”
    2.73
    姈
    2.72
    聍
    2.72
    随即
    2.69
     sabid
    2.69
    Activations Density 0.048%

    No Known Activations