© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 11491
    Prev
    Next
    INDEX
    Explanations

    customer service or help

    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
     cuarenta
    -1.12
     cincuenta
    -1.09
     Hôtel
    -1.06
    dirond
    -1.02
     hôtel
    -1.02
    Q
    -1.02
     slutet
    -1.00
    EDU
    -0.99
    STEM
    -0.99
     treinta
    -0.98
    POSITIVE LOGITS
     services
    1.75
     service
    1.28
     Services
    1.14
     töö
    1.09
     business
    1.09
    formik
    1.05
     palvel
    1.04
     nice
    1.02
     businesses
    1.02
     company
    0.99
    Activations Density 0.003%

    No Known Activations