© 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. 90626
    Prev
    Next
    INDEX
    Explanations

    jetbrains.mps, annotations, carboxylic acid

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

    non-English characters and technical terms in programming-related 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_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
    也将
    -2.77
    遄
    -2.75
    .
    -2.67
    洐
    -2.63
    锱
    -2.61
    quelize
    -2.59
     boken
    -2.56
     situato
    -2.50
    廡
    -2.50
    izoen
    -2.44
    POSITIVE LOGITS
    "
    2.88
    LLAB
    2.38
    鴆
    2.31
    VIATIONS
    2.28
    %;
    2.28
    苙
    2.23
     voyages
    2.20
     ")";
    2.16
     intonation
    2.11
    stateMutability
    2.09
    Activations Density 0.001%

    No Known Activations