© 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. 12364
    Prev
    Next
    INDEX
    Explanations

    foreign language and codes

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

    text in non-English languages, particularly Asian languages like Chinese and Japanese.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     möglichen
    -2.72
     notwendigen
    -2.59
    簠
    -2.58
     perfecte
    -2.52
    ᨆ
    -2.50
     ihe
    -2.45
    黢
    -2.44
    <bos>
    -2.44
     Gefahren
    -2.39
    鹋
    -2.38
    POSITIVE LOGITS
    This
    3.09
     What
    2.86
    y
    2.75
     That
    2.69
    The
    2.67
    s
    2.61
    what
    2.44
     For
    2.42
     This
    2.38
    來的
    2.36
    Activations Density 0.000%

    No Known Activations