© 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. 89908
    Prev
    Next
    INDEX
    Explanations

    Sara/Sarah names and locations

    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
    tels
    -0.77
    ◻
    -0.77
     WebDriver
    -0.75
    裆
    -0.75
     xvii
    -0.74
    原材料
    -0.74
     Tant
    -0.73
    isit
    -0.71
    ⌗
    -0.71
     Nutzungs
    -0.70
    POSITIVE LOGITS
    オフ
    0.87
     Sar
    0.79
    topRight
    0.73
     sar
    0.73
    匂
    0.72
    бит
    0.71
     vapor
    0.66
    작
    0.65
     متری
    0.65
     notices
    0.65
    Activations Density 0.034%

    No Known Activations