© 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. 117285
    Prev
    Next
    INDEX
    Explanations

    data compression formats

    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
     trá
    -0.81
     annuel
    -0.77
    dym
    -0.76
    sscanf
    -0.76
     voulez
    -0.73
     །
    -0.72
    pesar
    -0.72
     niño
    -0.69
    udahkan
    -0.69
     stimm
    -0.69
    POSITIVE LOGITS
     compression
    4.03
     compress
    3.52
     Compression
    3.48
    compression
    3.34
    Compression
    3.30
    compress
    3.17
    压缩
    3.17
     compressed
    2.91
     compressors
    2.88
    Compress
    2.75
    Activations Density 0.103%

    No Known Activations