© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 80855
    Prev
    Next
    INDEX
    Explanations

    android file paths

    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
     CSV
    -0.77
     clips
    -0.76
    Detal
    -0.75
    натор
    -0.72
     LEGO
    -0.71
     Dusty
    -0.71
    ROLS
    -0.69
    糞
    -0.68
    贪
    -0.68
    zete
    -0.68
    POSITIVE LOGITS
     radiology
    0.82
    rões
    0.81
    ByteArray
    0.78
    Letter
    0.77
     StringIO
    0.76
     ImageIcon
    0.75
     mutagen
    0.75
     ネックレス
    0.74
     Imaging
    0.74
     ۱۳۹
    0.73
    Activations Density 0.005%

    No Known Activations