© 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. 22-GEMMASCOPE-RES-131K
    7. 25585
    Prev
    Next
    INDEX
    Explanations

    sql queries and commands

    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_22/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
    潆
    -2.97
     They
    -2.94
    pecabe
    -2.58
    鹮
    -2.56
    ୩
    -2.28
    䊐
    -2.25
    Ꮬ
    -2.22
    聼
    -2.19
    
    -2.16
    是如何
    -2.14
    POSITIVE LOGITS
    秾
    3.42
    鉭
    3.08
    Y
    3.00
    瓩
    2.55
    te
    2.48
    
    2.48
    E
    2.42
    D
    2.41
    最後
    2.41
     uninterrupted
    2.38
    Activations Density 0.014%

    No Known Activations