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. 7729
    Prev
    Next
    INDEX
    Explanations

    script execution

    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
    ː
    -0.77
    VertexArray
    -0.74
    platten
    -0.73
     singer
    -0.72
    歪
    -0.71
    JAXB
    -0.70
    vetrain
    -0.69
    插
    -0.69
     JSTOR
    -0.69
    صة
    -0.69
    POSITIVE LOGITS
     shell
    2.77
     bash
    2.33
    Shell
    2.28
     Shell
    2.28
    shell
    2.27
     script
    2.25
     scripts
    2.08
     Bash
    1.91
    sh
    1.87
    SHELL
    1.87
    Activations Density 0.291%

    No Known Activations