© 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. 100462
    Prev
    Next
    INDEX
    Explanations

    Mac/Mc names and abbreviations

    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
    
    -2.67
    髎
    -2.67
    ⾳
    -2.63
    饜
    -2.58
    屨
    -2.48
     uſed
    -2.47
     incluem
    -2.42
     イラストレーション
    -2.39
    僦
    -2.39
    嫑
    -2.38
    POSITIVE LOGITS
    in
    2.97
    as
    2.70
    In
    2.63
    された
    2.52
     "
    2.45
    r
    2.44
     t
    2.42
    l
    2.39
    蛧
    2.34
    n
    2.33
    Activations Density 0.004%

    No Known Activations