© 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. 22-GEMMASCOPE-RES-131K
    7. 98426
    Prev
    Next
    INDEX
    Explanations

    programming code and its syntax

    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_22/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
    果
    -1.05
     føl
    -0.94
     presentarse
    -0.92
     uovo
    -0.92
     sinnvoll
    -0.90
     virkelig
    -0.90
    graham
    -0.88
    骸
    -0.86
    congress
    -0.86
    挲
    -0.86
    POSITIVE LOGITS
    ₚ
    0.90
     of
    0.88
     who
    0.85
    āya
    0.84
    一張
    0.82
    Meanwhile
    0.81
    asString
    0.79
     Saxon
    0.78
    chè
    0.78
    Только
    0.77
    Activations Density 0.003%

    No Known Activations