Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 199
    Prev
    Next
    INDEX
    Explanations

    business travel and expenses

    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
     Saltar
    -1.30
     Să
    -1.27
     coloridas
    -1.21
     reaksi
    -1.21
     coloridos
    -1.21
    protoimpl
    -1.20
    CÓ
    -1.20
     lamenta
    -1.19
    plotlib
    -1.19
     teknik
    -1.17
    POSITIVE LOGITS
     when
    1.38
    تها
    1.30
     for
    1.29
    的一个
    1.27
    When
    1.23
    on
    1.21
    gies
    1.18
     таких
    1.17
    ITY
    1.16
    了一个
    1.16
    Activations Density 0.025%

    No Known Activations