© 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. 276
    Prev
    Next
    INDEX
    Explanations

    to destinations

    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
    <bos>
    -1.63
    なかった
    -1.43
    尴
    -1.39
     blauw
    -1.34
     silicona
    -1.34
    AILED
    -1.34
    复制代码
    -1.33
     although
    -1.31
     Masih
    -1.31
    amaño
    -1.30
    POSITIVE LOGITS
     to
    2.47
     the
    1.95
    0
    1.64
    The
    1.57
     đến
    1.44
     Therefore
    1.39
     október
    1.38
    }$
    1.34
    什麼
    1.34
     The
    1.32
    Activations Density 0.039%

    No Known Activations