© 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. 14418
    Prev
    Next
    INDEX
    Explanations

    names Denis Friedrich Sasha

    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
    '
    -3.31
    𓆜
    -3.22
    We
    -3.17
    er
    -3.00
    So
    -2.88
    .”
    -2.86
    e
    -2.73
     путем
    -2.45
    As
    -2.42
    谞
    -2.39
    POSITIVE LOGITS
    鷙
    3.19
     ausein
    2.88
    抟
    2.64
    
    2.52
    鬭
    2.50
    筇
    2.50
    歘
    2.41
     память
    2.39
    戕
    2.38
    乁
    2.33
    Activations Density 0.005%

    No Known Activations