© 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. 34-GEMMASCOPE-RES-131K
    7. 2363
    Prev
    Next
    INDEX
    Explanations

    various languages and scripts

    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_34/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
    他才
    -1.11
    ﹔
    -1.07
    "—
    -1.05
    ”—
    -1.01
     wüns
    -1.01
    の中では
    -1.01
    »:
    -1.00
     toallas
    -0.98
     obecnie
    -0.98
     می‌شود
    -0.97
    POSITIVE LOGITS
    お世話
    1.11
    图片来源
    1.10
    𐌱
    1.08
     Peraturan
    1.06
    schuhe
    1.05
     endeav
    1.05
    Manfaat
    1.02
    的过程
    1.02
    Слу
    1.02
    Lokasi
    1.01
    Activations Density 0.072%

    No Known Activations