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. 22-GEMMASCOPE-2-RES-16K
    4. 238
    Prev
    Next
    INDEX
    Explanations

    URLs ending in .com

    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_22_width_16k_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
     isol
    0.50
    е
    0.48
     через
    0.46
    ,
    0.46
     using
    0.45
     sel
    0.45
     menggunakan
    0.45
     с
    0.44
     decor
    0.42
     meng
    0.42
    POSITIVE LOGITS
    Thank
    0.90
    Hope
    0.88
     Thank
    0.80
    Notable
    0.79
    Hopefully
    0.78
    People
    0.78
    Sorry
    0.77
    Thanks
    0.77
    Their
    0.77
     enterprising
    0.76
    Activations Density 0.415%

    No Known Activations