© 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. 1315
    Prev
    Next
    INDEX
    Explanations

    scientific citations

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

    volume and page numbers in scientific journal citations.

    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
     bautizo
    -1.92
     fallecimiento
    -1.73
    middels
    -1.64
    らなかった
    -1.59
     sierp
    -1.59
    地看着
    -1.57
    かも知
    -1.57
    habited
    -1.51
     ähnlichen
    -1.49
     espectáculos
    -1.49
    POSITIVE LOGITS
     it
    1.88
     more
    1.76
     such
    1.69
     some
    1.65
     encontr
    1.55
    <bos>
    1.52
     something
    1.49
     lelaki
    1.49
     a
    1.48
    AHUL
    1.47
    Activations Density 0.023%

    No Known Activations