© 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. 101695
    Prev
    Next
    INDEX
    Explanations

    years ago

    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
    푢
    -2.02
     to
    -1.92
     for
    -1.83
     mentales
    -1.59
    конструк
    -1.54
     uſed
    -1.53
    ☺☺
    -1.50
     towards
    -1.49
     vooral
    -1.49
    stateMutability
    -1.48
    POSITIVE LOGITS
    ↵
    1.71
     zesta
    1.70
     ago
    1.59
     last
    1.58
    了嗎
    1.55
    ↵↵
    1.54
    ,
    1.45
     I
    1.44
    、
    1.41
     my
    1.40
    Activations Density 0.019%

    No Known Activations