© 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. 83160
    Prev
    Next
    INDEX
    Explanations

    Cartilage, numerical judgments

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

    XML and technical markup elements in 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
     what
    -1.10
     both
    -1.02
     all
    -0.92
     their
    -0.86
     helped
    -0.85
     enhanced
    -0.82
     huge
    -0.81
    態度
    -0.80
     widely
    -0.80
     an
    -0.80
    POSITIVE LOGITS
    ̀i
    0.89
     arduino
    0.85
    vores
    0.85
     THOR
    0.84
     dvd
    0.84
     CSI
    0.83
    iol
    0.82
     Xcode
    0.82
    waran
    0.82
    unton
    0.82
    Activations Density 0.000%

    No Known Activations