© 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. 29-GEMMASCOPE-2-RES-16K
    7. 788
    Prev
    Next
    INDEX
    Explanations

    at least

    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_29_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
    hots
    0.73
    ရ
    0.71
     datasets
    0.69
     format
    0.69
     cogniz
    0.68
    ात
    0.67
    形
    0.67
     আরেকটি
    0.67
    дной
    0.67
    ᅡ
    0.66
    POSITIVE LOGITS
     least
    2.28
    least
    1.78
    Least
    1.59
     Least
    1.55
     odds
    1.26
     times
    1.25
     night
    1.09
    razine
    1.09
     risk
    1.07
     stake
    1.07
    Activations Density 0.162%

    No Known Activations