© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-16K
    7. 9576
    Prev
    Next
    INDEX
    Explanations

    DNS records and headlines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
    to
    0.70
    re
    0.68
    m
    0.68
    in
    0.66
    s
    0.63
    li
    0.61
    can
    0.61
    was
    0.55
    llä
    0.55
    mentation
    0.55
    POSITIVE LOGITS
     rivet
    0.61
     be
    0.57
     espl
    0.55
    ৫
    0.54
     cheg
    0.54
     ouvertes
    0.54
     suffis
    0.52
     miš
    0.51
    つの
    0.50
    けた
    0.50
    Activations Density 2.557%

    No Known Activations