© 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. 80916
    Prev
    Next
    INDEX
    Explanations

    microsoft api documentation

    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
     broderie
    -0.76
    INUM
    -0.73
     स्थान
    -0.72
    dett
    -0.71
     franc
    -0.71
    removeClass
    -0.70
    rasse
    -0.69
    ♮
    -0.69
     cus
    -0.69
     味
    -0.69
    POSITIVE LOGITS
     habiendo
    0.75
     api
    0.74
     API
    0.73
    microsoft
    0.72
     classiques
    0.71
    comfortably
    0.70
     aprilie
    0.70
     maid
    0.70
    izedBox
    0.70
    API
    0.70
    Activations Density 0.037%

    No Known Activations