© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 123779
    Prev
    Next
    INDEX
    Explanations

    MEDLINE and literature search

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

    database names like MEDLINE and academic/scientific terminology.

    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
     to
    -1.84
     verhind
    -1.48
     vastly
    -1.46
     dando
    -1.44
     nuove
    -1.41
     diversos
    -1.39
     ofrecen
    -1.38
     reciben
    -1.38
     hugely
    -1.34
     numerosi
    -1.34
    POSITIVE LOGITS
     and
    2.47
     which
    1.55
     prevents
    1.49
     what
    1.49
     creates
    1.45
    劻
    1.44
     seeks
    1.43
     makes
    1.42
    古屋
    1.41
     analysis
    1.40
    Activations Density 0.202%

    No Known Activations