© 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. 73871
    Prev
    Next
    INDEX
    Explanations

    zeros and ones

    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
    鹋
    -2.06
     Können
    -2.05
    ⎆
    -2.00
    囘
    -1.91
    鸲
    -1.87
    毉
    -1.83
    在她
    -1.82
    </h2>
    -1.70
     anstatt
    -1.66
     faux
    -1.65
    POSITIVE LOGITS
    </u>
    2.50
    lepaskan
    2.11
    "
    1.96
    ),
    1.77
     Дру
    1.73
    ↵↵
    1.71
     sáb
    1.66
    '
    1.60
     all
    1.59
    .,
    1.59
    Activations Density 0.001%

    No Known Activations