© 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. 84448
    Prev
    Next
    INDEX
    Explanations

    arcade and Armada

    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
    re
    -2.95
    艄
    -2.77
    ⟝
    -2.47
    呖
    -2.27
     It
    -2.27
    not
    -2.25
    2
    -2.22
    谵
    -2.20
    那时候
    -2.19
    
    -2.19
    POSITIVE LOGITS
     برانيه
    2.69
    versario
    2.67
    白玉
    2.44
    bangun
    2.44
     arcade
    2.28
    玊
    2.20
     selben
    2.17
    τικών
    2.16
    東南
    2.14
     šed
    2.13
    Activations Density 0.004%

    No Known Activations