© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 89713
    Prev
    Next
    INDEX
    Explanations

    internal borders superimposed Testing

    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_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    do
    0.55
    ta
    0.52
    Lock
    0.51
    tune
    0.46
    ко
    0.46
    lock
    0.45
    o
    0.45
    to
    0.44
    łon
    0.44
    tai
    0.44
    POSITIVE LOGITS
    userID
    0.49
     APPROVED
    0.47
    很大的
    0.47
     Wikip
    0.46
    ُوا
    0.46
     కూడా
    0.44
    动漫
    0.44
    如下
    0.44
     উৎসব
    0.44
     profitieren
    0.43
    Activations Density 0.002%

    No Known Activations