© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13719
    Prev
    Next
    INDEX
    Explanations

    Caucasian people and regions

    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
     But
    -2.72
    玧
    -2.41
     miliardi
    -2.33
    雠
    -2.33
     unſ
    -2.30
     settimane
    -2.28
    ."));
    -2.23
    1
    -2.22
    饪
    -2.19
    杁
    -2.19
    POSITIVE LOGITS
    </sup>
    2.36
    請繼續
    1.89
    dijual
    1.84
    日を
    1.80
    苹
    1.78
    ILERS
    1.77
    封印
    1.75
    擎
    1.72
     fairytale
    1.72
     Ее
    1.71
    Activations Density 0.002%

    No Known Activations