© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57386
    Prev
    Next
    INDEX
    Explanations

    inventory, supervised, pharmacists, agreed, was carried

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

    formal document or legal text elements, particularly in research papers, reports, and administrative documents.

    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
    的人生
    -0.89
    台中
    -0.89
     médié
    -0.84
    agus
    -0.81
    bion
    -0.80
    近年来
    -0.77
    appé
    -0.76
    기도
    -0.75
     Gum
    -0.75
    Año
    -0.75
    POSITIVE LOGITS
    瀕
    0.87
    動物園
    0.87
    pstmt
    0.81
    тою
    0.80
    Reentrant
    0.80
     schlaf
    0.79
    Ϯ
    0.79
    Več
    0.79
    >)</
    0.78
     außergewöhn
    0.78
    Activations Density 0.029%

    No Known Activations