© 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. 70795
    Prev
    Next
    INDEX
    Explanations

    human beings

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

    the beginning of phrases where someone identifies their professional or personal role before making a statement.

    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
     for
    -1.31
     darbu
    -1.26
    rédients
    -1.18
     هستند
    -1.18
     in
    -1.14
     aspects
    -1.14
    一线
    -1.13
     with
    -1.13
     Câmara
    -1.13
    風味
    -1.10
    POSITIVE LOGITS
     both
    1.49
     recogida
    1.44
     then
    1.44
     zowel
    1.35
     tivi
    1.34
     quando
    1.31
     determinada
    1.31
     your
    1.31
     this
    1.29
    และ
    1.28
    Activations Density 0.028%

    No Known Activations