© 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. 8648
    Prev
    Next
    INDEX
    Explanations

    sexual health and remedies

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

    titles or headings related to pharmaceutical or medication products, especially Viagra and other prescription drugs.

    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
     it
    -1.71
    0
    -1.70
    .
    -1.66
    Both
    -1.64
     of
    -1.63
    8
    -1.61
    4
    -1.57
     ؟
    -1.55
    (
    -1.53
    6
    -1.52
    POSITIVE LOGITS
    扨
    1.90
    ಱ
    1.77
    ebly
    1.66
     unſ
    1.61
    閦
    1.59
    强制
    1.56
    铊
    1.55
    麁
    1.53
    unno
    1.52
    厠
    1.52
    Activations Density 0.020%

    No Known Activations