© 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. 12420
    Prev
    Next
    INDEX
    Explanations

    entities and their actions

    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
     ESPEC
    -0.93
    ớp
    -0.90
    GIUM
    -0.87
     nahmen
    -0.86
     \
    -0.86
     огромное
    -0.85
    江西
    -0.84
     الجميع
    -0.82
     dissol
    -0.81
    Руко
    -0.81
    POSITIVE LOGITS
     patients
    1.23
     customers
    1.13
     customer
    1.04
     patient
    1.03
     auch
    0.99
     businesses
    0.96
     companies
    0.95
    clusal
    0.94
     content
    0.91
     goods
    0.91
    Activations Density 0.461%

    No Known Activations