© 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. 54382
    Prev
    Next
    INDEX
    Explanations

    URL paths and parameters

    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
    '}';
    -1.03
     roster
    -0.98
     فريبيس
    -0.91
     fuzz
    -0.91
     Police
    -0.90
     penis
    -0.89
     Fähigkeit
    -0.89
     是
    -0.88
    使用的
    -0.88
     polska
    -0.87
    POSITIVE LOGITS
    追記
    0.96
    特斯拉
    0.96
    為に
    0.93
     caverns
    0.93
    ៀ
    0.93
    補足
    0.92
    temporada
    0.92
    موس
    0.90
    کتاب
    0.89
    ＊＊＊＊
    0.86
    Activations Density 0.002%

    No Known Activations