© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 13611
    Prev
    Next
    INDEX
    Explanations

    C++ standard library types

    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
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -2.03
     For
    -1.94
    ↵↵↵↵↵↵↵↵↵↵
    -1.92
    ↵↵↵↵↵↵↵↵↵↵↵↵↵
    -1.88
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -1.86
    !!"
    -1.82
     Then
    -1.82
     beiden
    -1.81
    ↵↵↵↵↵↵↵↵↵↵↵
    -1.80
    。"
    -1.80
    POSITIVE LOGITS
     you
    2.11
     från
    2.06
     休閒
    1.85
    eadilan
    1.70
     dolar
    1.66
     botines
    1.65
     avantage
    1.63
    閹
    1.63
     erros
    1.61
    鏟
    1.60
    Activations Density 0.003%

    No Known Activations