© 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. 76360
    Prev
    Next
    INDEX
    Explanations

    code comments and headers

    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
    况
    -0.80
    ovan
    -0.76
    ဟ
    -0.75
     harassed
    -0.75
     Gegner
    -0.73
    note
    -0.72
    に行ってきました
    -0.70
    럭
    -0.69
     assaulting
    -0.69
    贰
    -0.69
    POSITIVE LOGITS
    Figure
    1.03
    Fig
    0.99
    ↵↵↵↵↵↵↵
    0.93
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.81
    ↵↵↵↵↵↵↵↵↵
    0.81
    हरु
    0.79
    ↵↵↵↵↵↵
    0.77
    ↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.76
    ↵↵↵↵↵↵↵↵↵↵↵↵
    0.73
    ↵↵↵
    0.73
    Activations Density 0.013%

    No Known Activations