© 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. 10-GEMMASCOPE-RES-131K
    7. 90686
    Prev
    Next
    INDEX
    Explanations

    legally liable for damages

    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
    浤
    -2.27
     éditoriale
    -2.14
    嚆
    -2.05
    zembro
    -2.02
    你和
    -1.98
    噥
    -1.95
     murale
    -1.94
    ﻂ
    -1.93
     решили
    -1.93
    龘
    -1.92
    POSITIVE LOGITS
     they
    2.16
     to
    2.13
    饪
    1.95
    .
    1.92
     também
    1.78
    O
    1.72
     for
    1.61
     su
    1.56
    楽しめる
    1.55
    みを
    1.52
    Activations Density 0.005%

    No Known Activations