© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 78743
    Prev
    Next
    INDEX
    Explanations

    PubMed literature search

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

    references to academic databases like PubMed in scientific papers.

    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
    くださいね
    -0.85
     переза
    -0.80
    primaryKey
    -0.77
     maakt
    -0.77
    tradu
    -0.77
     podemos
    -0.76
     предотвра
    -0.76
     также
    -0.75
    駐車場
    -0.75
    酥
    -0.73
    POSITIVE LOGITS
     pleine
    0.84
    WebApp
    0.81
     Exempt
    0.81
    咐
    0.81
    lancer
    0.80
    сторія
    0.80
    вної
    0.79
     visit
    0.79
    僖
    0.78
     cortinas
    0.77
    Activations Density 0.006%

    No Known Activations