© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 103733
    Prev
    Next
    INDEX
    Explanations

    viruses

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

    HTTP protocol version indicators (HTTP/1.1) and location paths in URLs.

    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_10/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
     because
    -1.59
     when
    -1.50
    它的
    -1.48
     are
    -1.47
     kemudian
    -1.45
     problems
    -1.38
     produces
    -1.35
     These
    -1.34
     Rechten
    -1.33
     each
    -1.31
    POSITIVE LOGITS
    ignez
    1.41
    yatı
    1.37
     интерьере
    1.31
     большинстве
    1.29
    あなたが
    1.29
     peup
    1.28
    哐
    1.27
    我没
    1.26
    ৢ
    1.25
     như
    1.23
    Activations Density 0.016%

    No Known Activations