© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 16067
    Prev
    Next
    INDEX
    Explanations

    exit and return from functions

    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_17_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
     ficha
    0.84
    ismer
    0.76
     بیشتر
    0.71
    را
    0.70
     ur
    0.70
    dinger
    0.69
    𝖚
    0.69
    renc
    0.69
     दिसम्बर
    0.68
     bila
    0.68
    POSITIVE LOGITS
     PCIe
    0.80
     ﷺ
    0.76
     Geological
    0.75
     Buffalo
    0.74
    किस्तान
    0.73
     bokeh
    0.72
     vegetative
    0.71
     photosphere
    0.71
     therefore
    0.70
     Minneapolis
    0.70
    Activations Density 0.219%

    No Known Activations