© 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. 103938
    Prev
    Next
    INDEX
    Explanations

    package and consumers

    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
    lihatkan
    -0.87
     اینجا
    -0.86
    ("+
    -0.85
    ımda
    -0.85
     square
    -0.85
    Fá
    -0.79
    getDay
    -0.79
    ركز
    -0.79
    adering
    -0.79
     сначала
    -0.79
    POSITIVE LOGITS
    ucción
    0.94
    ypos
    0.84
     ര
    0.82
    🩹
    0.82
     Queen
    0.77
    linalg
    0.77
     have
    0.76
     its
    0.75
    енко
    0.75
     you
    0.74
    Activations Density 0.087%

    No Known Activations