© 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. 48471
    Prev
    Next
    INDEX
    Explanations

    legal filings and local places

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    赂
    -1.49
     the
    -1.45
     beinahe
    -1.36
     риск
    -1.33
    々な
    -1.33
     imagination
    -1.30
    散发
    -1.30
    вгений
    -1.30
     einfacher
    -1.29
     schwerer
    -1.29
    POSITIVE LOGITS
     their
    1.78
    ”،
    1.77
    ле
    1.69
    ”)
    1.63
    ”),
    1.59
     For
    1.49
    しゃれ
    1.48
    聍
    1.48
     ラーメン
    1.45
    henge
    1.44
    Activations Density 0.004%

    No Known Activations