© 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. 48343
    Prev
    Next
    INDEX
    Explanations

    header sections

    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
     peixe
    -0.72
    >(&
    -0.71
    ▫
    -0.67
    }^{(
    -0.67
     trink
    -0.65
    ревно
    -0.65
     resentment
    -0.64
     wiele
    -0.63
    ismuth
    -0.63
     незавершена
    -0.63
    POSITIVE LOGITS
     Header
    1.13
     header
    1.13
    header
    1.11
    Header
    0.90
    layout
    0.85
    きましたが
    0.81
     HEADER
    0.80
    COGN
    0.77
     dodge
    0.76
    PHeader
    0.76
    Activations Density 0.007%

    No Known Activations