© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 99277
    Prev
    Next
    INDEX
    Explanations

    carboxylic acid

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

    words and syllables in non-English languages, particularly Slavic and Eastern European languages.

    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
    。"
    -1.83
    ?"
    -1.68
    𝐖
    -1.66
     ultime
    -1.66
     forState
    -1.60
    зив
    -1.59
    亲爱的
    -1.58
     ресурсы
    -1.56
    Semua
    -1.56
    the
    -1.56
    POSITIVE LOGITS
     übrigens
    1.95
    匆
    1.84
     We
    1.80
     außerdem
    1.77
     ursprünglich
    1.76
    makeat
    1.69
     siguiendo
    1.66
    这般
    1.65
     Aktivität
    1.64
    ”.
    1.62
    Activations Density 0.065%

    No Known Activations