© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 2331
    Prev
    Next
    INDEX
    Explanations

    directions and movements

    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
     being
    -0.80
     также
    -0.79
    んでいる
    -0.77
    zydent
    -0.77
     санк
    -0.76
    เท้า
    -0.74
    atual
    -0.73
    تب
    -0.73
    imread
    -0.73
     marbles
    -0.72
    POSITIVE LOGITS
     turn
    1.10
     turns
    0.96
     left
    0.91
     twice
    0.88
     turnaround
    0.87
    turn
    0.86
    Right
    0.84
     lança
    0.84
    了两
    0.83
     right
    0.83
    Activations Density 0.006%

    No Known Activations