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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-262K
    4. 7478
    Prev
    Next
    INDEX
    Explanations

    for example

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ة
    1.60
    ed
    1.18
    ت
    1.05
     fabricante
    1.02
     tablespoons
    1.02
    я
    1.01
    ️
    1.01
    ⅔
    0.98
    ০০০
    0.97
    es
    0.96
    POSITIVE LOGITS
    erun
    1.47
     reasons
    1.36
     example
    1.22
    giveness
    1.21
    erunner
    1.19
     sake
    1.19
     instance
    1.16
     purposes
    1.14
    asmuch
    1.14
    対流
    1.13
    Activations Density 0.548%

    No Known Activations