© 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. 9-GEMMASCOPE-2-RES-16K
    7. 284
    Prev
    Next
    INDEX
    Explanations

    languages in numbered lists

    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_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
    in
    0.70
    surprisingly
    0.63
    socks
    0.63
    inę
    0.63
    х
    0.62
    inode
    0.59
    ar
    0.58
    categor
    0.58
    iduría
    0.58
    
    0.58
    POSITIVE LOGITS
    j
    0.70
    &\
    0.60
    oted
    0.58
    ۰۰
    0.58
    ja
    0.57
    ્ઞ
    0.57
    క
    0.55
    ての
    0.55
    0
    0.55
    ሲ
    0.55
    Activations Density 4.625%

    No Known Activations