© 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. 34-GEMMASCOPE-RES-131K
    7. 31559
    Prev
    Next
    INDEX
    Explanations

    colors following assignments

    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_34/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
    与此同时
    -0.98
    ’
    -0.98
    ナビ
    -0.95
     шанс
    -0.95
     stiller
    -0.93
    terrasse
    -0.92
    配色
    -0.91
     reiz
    -0.91
     caos
    -0.89
    cences
    -0.89
    POSITIVE LOGITS
     white
    2.09
     black
    1.93
    white
    1.74
     gray
    1.69
     red
    1.66
     green
    1.65
     White
    1.49
     grey
    1.43
     blue
    1.40
     brown
    1.39
    Activations Density 0.010%

    No Known Activations