© 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. 61149
    Prev
    Next
    INDEX
    Explanations

    code statements ending in semicolon

    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
     realmente
    -1.70
    }})
    -1.47
     reprezenta
    -1.32
    така
    -1.30
     totalmente
    -1.27
    䜣
    -1.27
    ❯
    -1.27
    }`;
    -1.26
    Ҭ
    -1.26
     completamente
    -1.25
    POSITIVE LOGITS
    ↵↵
    2.16
     這
    1.52
    闖
    1.50
     may
    1.49
     you
    1.48
    Also
    1.45
     particularly
    1.41
    However
    1.41
    Those
    1.39
     zusätzlichen
    1.39
    Activations Density 0.037%

    No Known Activations