© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 74310
    Prev
    Next
    INDEX
    Explanations

    parts of words or different languages

    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
    栳
    -3.39
    を始め
    -2.86
    佧
    -2.75
    engertian
    -2.69
     "";
    -2.69
    ⚢
    -2.67
    咴
    -2.58
     \
    -2.56
    鬭
    -2.55
    
    -2.53
    POSITIVE LOGITS
    s
    3.81
    </i>
    3.14
     It
    2.98
    r
    2.91
     たら
    2.50
    uy
    2.48
    ol
    2.47
    iv
    2.42
    ion
    2.39
     Their
    2.34
    Activations Density 0.021%

    No Known Activations