© 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. 105240
    Prev
    Next
    INDEX
    Explanations

    foreign languages and code

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

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

    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
    SOME
    -1.58
     recentemente
    -1.39
     ผู้
    -1.35
     MAJOR
    -1.33
    </code>
    -1.31
    URBAN
    -1.31
    NIGHT
    -1.26
    moreland
    -1.26
     BRAIN
    -1.26
     fata
    -1.25
    POSITIVE LOGITS
     your
    2.13
     both
    2.06
     more
    1.99
     a
    1.99
     any
    1.94
     this
    1.92
     really
    1.80
     great
    1.79
     our
    1.78
     surprisingly
    1.77
    Activations Density 0.003%

    No Known Activations