© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 12199
    Prev
    Next
    INDEX
    Explanations

    proper names, surnames, acronyms

    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
    ︓
    -2.44
     Anſ
    -2.42
     With
    -2.41
    In
    -2.34
    諜
    -2.34
     Despite
    -2.33
    骝
    -2.30
     In
    -2.28
    推荐阅读
    -2.28
    ---------
    -2.27
    POSITIVE LOGITS
     vielen
    2.86
     immense
    2.69
    </strong>
    2.67
     crucial
    2.58
     terrific
    2.56
     preocu
    2.55
     financieros
    2.50
    崤
    2.42
     usual
    2.41
    性は
    2.41
    Activations Density 0.040%

    No Known Activations