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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B
    3. 29-GEMMASCOPE-2-RES-16K
    4. 3081
    Prev
    Next
    INDEX
    Explanations

    project file paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     /*
    0.68
     {/*
    0.67
     JOptionPane
    0.63
     :,
    0.62
    :「
    0.59
    :“
    0.59
    <a>
    0.58
    (“
    0.58
     કર
    0.58
     FileInputStream
    0.57
    POSITIVE LOGITS
    utils
    1.39
    models
    1.38
     utils
    1.28
    helpers
    1.28
    utilities
    1.27
     models
    1.21
     utilities
    1.20
    ../../
    1.15
    Helpers
    1.14
    Models
    1.12
    Activations Density 0.019%

    No Known Activations