© 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. 4367
    Prev
    Next
    INDEX
    Explanations

    unsigned integer types

    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
    kování
    -0.94
    تيجة
    -0.92
     también
    -0.90
    <0x17>
    -0.90
     cuno
    -0.89
    čit
    -0.83
    jeen
    -0.83
     spodnie
    -0.83
    kover
    -0.82
     캐릭터
    -0.82
    POSITIVE LOGITS
     with
    0.75
     باشه
    0.75
    if
    0.74
     to
    0.73
     staunch
    0.73
     \
    0.72
    NC
    0.71
     these
    0.70
     utilized
    0.69
    <>
    0.69
    Activations Density 0.026%

    No Known Activations