© 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. 34-GEMMASCOPE-RES-131K
    7. 108625
    Prev
    Next
    INDEX
    Explanations

    Wright, offers, Regional anesthesia, Bloody Spear

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

    names of people, especially surnames like "Wright", often in professional or legal contexts.

    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
    为大家
    -0.84
    lentes
    -0.81
    зме
    -0.80
    talet
    -0.79
    ctividad
    -0.79
     moat
    -0.76
    setData
    -0.75
    ляем
    -0.75
     Boiler
    -0.73
    Palo
    -0.73
    POSITIVE LOGITS
    uş
    0.76
     Wright
    0.76
     discounts
    0.73
     wäre
    0.73
     offers
    0.73
    伦
    0.70
    剪
    0.69
     oferece
    0.69
    citep
    0.68
     مسی
    0.68
    Activations Density 0.014%

    No Known Activations