© 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. 12423
    Prev
    Next
    INDEX
    Explanations

    medical marijuana

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

    titles or headers at the beginning of articles or documents.

    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
     with
    -1.67
     to
    -1.64
     that
    -1.63
    </u>
    -1.34
    EDAD
    -1.30
    _
    -1.29
    に戻る
    -1.28
     (“
    -1.27
    )
    -1.26
     スクリーン
    -1.24
    POSITIVE LOGITS
     Saltar
    1.72
    tômes
    1.44
     "
    1.39
    Дереккөздер
    1.37
     принципе
    1.34
    1
    1.34
     pemer
    1.30
    aneity
    1.27
    Leírás
    1.26
    quisar
    1.25
    Activations Density 0.323%

    No Known Activations