© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 185663
    Prev
    Next
    INDEX
    Explanations

    to get, vote, opt

    np_acts-logits-general · gemini-2.5-flash-lite

    sacrificing individual well-being

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    reflectionMap
    0.52
    我们也
    0.50
     substrings
    0.49
    糈
    0.47
     kinases
    0.44
     vowels
    0.44
     miRNAs
    0.44
     Epoxy
    0.44
     \%$,
    0.43
    这将
    0.43
    POSITIVE LOGITS
    com
    0.48
    mur
    0.48
    S
    0.44
    N
    0.43
    cko
    0.42
    haw
    0.41
    Č
    0.41
    Watch
    0.41
    se
    0.40
     Gandhi
    0.40
    Activations Density 0.001%

    No Known Activations