© 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. 10-GEMMASCOPE-RES-131K
    7. 86886
    Prev
    Next
    INDEX
    Explanations

    medical conditions, treatment, or specific events

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

    technical or specialized terms across different domains like science, mathematics, and technical fields.

    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
    par
    -1.52
    _
    -1.50
    er
    -1.48
    (
    -1.45
    ()
    -1.39
    w
    -1.34
    着一个
    -1.32
    to
    -1.31
    pr
    -1.30
    ariats
    -1.28
    POSITIVE LOGITS
     they
    1.73
     predecess
    1.65
     suono
    1.63
     sonno
    1.62
    inspira
    1.58
     meravigli
    1.55
     dasarnya
    1.55
    رأة
    1.52
     their
    1.51
     used
    1.51
    Activations Density 0.164%

    No Known Activations