© 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. 22-GEMMASCOPE-RES-131K
    7. 13528
    Prev
    Next
    INDEX
    Explanations

    multilingual code snippets

    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_22/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
    safari
    -0.81
     bianco
    -0.79
     自動
    -0.78
    編集部
    -0.78
    ⅘
    -0.77
    フィル
    -0.74
    攥
    -0.74
     Boles
    -0.74
    auth
    -0.74
    icap
    -0.74
    POSITIVE LOGITS
     gånger
    0.93
     with
    0.89
    produzione
    0.87
     между
    0.83
    assertRaises
    0.82
     никогда
    0.82
    峻
    0.82
    éis
    0.82
     tillgäng
    0.81
    ılığı
    0.80
    Activations Density 0.009%

    No Known Activations