© 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. 39901
    Prev
    Next
    INDEX
    Explanations

    African Republic

    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
    袂
    -1.96
    </h5>
    -1.96
    半个
    -1.88
    輅
    -1.82
    ܜ
    -1.78
    豪華
    -1.75
    okości
    -1.73
    肖像
    -1.73
    ный
    -1.72
    上の
    -1.72
    POSITIVE LOGITS
    𞤢
    2.13
    0
    2.13
    w
    1.86
    敺
    1.80
     kleines
    1.76
     besonderes
    1.75
    ↵↵
    1.72
    袮
    1.72
    这么
    1.71
    7
    1.70
    Activations Density 0.009%

    No Known Activations