© 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. 1174
    Prev
    Next
    INDEX
    Explanations

    programming and multi-language code snippets

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

    text written in non-Latin scripts, particularly Hebrew, Cyrillic, Chinese, and Arabic characters.

    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
    jogo
    -2.38
     Some
    -2.34
     murió
    -2.27
     Those
    -2.20
    な感じ
    -2.19
     наша
    -2.14
    ędzynarod
    -2.14
    ↵↵
    -2.13
     dahulu
    -2.11
     Interestingly
    -2.09
    POSITIVE LOGITS
    4
    3.48
    7
    3.27
    1
    3.08
    3
    2.95
    2
    2.83
    "
    2.69
    co
    2.63
    sh
    2.61
    5
    2.58
    ;
    
    2.53
    Activations Density 0.001%

    No Known Activations