© 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. 109265
    Prev
    Next
    INDEX
    Explanations

    naming and citations

    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
    平台
    -0.78
    系統
    -0.73
     Folks
    -0.73
    臨床
    -0.72
    くに
    -0.72
     Hump
    -0.72
     benzene
    -0.71
    поль
    -0.69
    ってきました
    -0.69
    alsh
    -0.69
    POSITIVE LOGITS
    zheim
    0.65
    encils
    0.65
     naming
    0.63
    anatom
    0.63
    浪漫
    0.60
    Sik
    0.60
    NRC
    0.59
    命名
    0.59
     online
    0.58
    Needed
    0.58
    Activations Density 0.071%

    No Known Activations