© 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. 66283
    Prev
    Next
    INDEX
    Explanations

    VT liver

    np_acts-logits-general · gemini-2.5-flash-lite

    newline characters in code and documentation files.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
    Admin
    -0.81
    原作
    -0.79
     Admin
    -0.79
     instagram
    -0.78
     reprezenta
    -0.75
    Intro
    -0.74
     Toner
    -0.73
    Instagram
    -0.72
     moda
    -0.71
     plataforma
    -0.69
    POSITIVE LOGITS
     VT
    1.26
    vt
    1.23
     vt
    1.11
    VT
    1.05
    Liver
    0.98
    Vt
    0.98
     livers
    0.96
     Liver
    0.90
    liver
    0.89
     củ
    0.83
    Activations Density 0.013%

    No Known Activations