© 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. 4135
    Prev
    Next
    INDEX
    Explanations

    it's or is followed by explanation

    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
    ul
    0.57
    emos
    0.56
    etr
    0.55
    
    0.55
    ária
    0.54
    Trace
    0.53
    ud
    0.53
    etz
    0.53
     lidí
    0.53
    လည်း
    0.53
    POSITIVE LOGITS
    ها
    0.80
     До
    0.76
     косми
    0.70
    ه
    0.70
     consonants
    0.70
    מ
    0.69
    ных
    0.68
     vegetative
    0.68
    ح
    0.67
    been
    0.66
    Activations Density 0.182%

    No Known Activations