© 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. 14391
    Prev
    Next
    INDEX
    Explanations

    finished tasks

    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
     czarna
    -2.02
     неболь
    -2.02
     czarne
    -1.97
    そういう
    -1.96
    "]));
    -1.94
    those
    -1.93
     the
    -1.91
     дополнительные
    -1.86
    3
    -1.84
     dzięki
    -1.83
    POSITIVE LOGITS
    🔔
    1.91
    💩
    1.83
     tille
    1.75
    🤪
    1.73
    ization
    1.71
    🌸
    1.67
    😫
    1.66
    🤡
    1.66
    👽
    1.66
    átiles
    1.65
    Activations Density 0.008%

    No Known Activations