© 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. 83378
    Prev
    Next
    INDEX
    Explanations

    copyright and license notices

    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
     Freundin
    -0.75
    新鲜
    -0.74
    ogenous
    -0.73
     بعدی
    -0.73
    SocketAddress
    -0.73
    找到
    -0.72
    tson
    -0.71
    igare
    -0.71
     apunt
    -0.71
    高达
    -0.68
    POSITIVE LOGITS
    Werk
    0.88
    āda
    0.85
     SCHED
    0.78
    netz
    0.78
     Reborn
    0.77
    contextMenu
    0.76
     suckers
    0.76
     decreto
    0.75
     postgres
    0.75
    éu
    0.75
    Activations Density 0.009%

    No Known Activations