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. 34-GEMMASCOPE-RES-131K
    4. 7638
    Prev
    Next
    INDEX
    Explanations

    Remembrance poppy veterans memorial

    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
    蜚
    -0.81
     비
    -0.81
    Vat
    -0.75
    ída
    -0.73
    Delete
    -0.71
     GIT
    -0.71
    }(),
    -0.71
    typeout
    -0.71
    译
    -0.69
    setTitle
    -0.68
    POSITIVE LOGITS
     poppy
    1.91
     poppies
    1.69
     Poppy
    1.64
    Poppy
    1.61
    poppy
    1.34
     veterans
    1.29
     Remembrance
    1.26
    Veterans
    1.23
     Veterans
    1.21
     Veteran
    1.14
    Activations Density 0.019%

    No Known Activations