© 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. 80351
    Prev
    Next
    INDEX
    Explanations

    advertising tobacco investing

    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
    ("***
    0.47
    晃
    0.41
    gio
    0.39
    ഞ്ഞ്
    0.38
    MODEL
    0.37
    gua
    0.37
    ("@
    0.36
    副作用
    0.36
    glazed
    0.36
    .~(\
    0.36
    POSITIVE LOGITS
    ম
    0.54
     Wyndham
    0.54
     قانونی
    0.52
     Ban
    0.52
    म
    0.52
     कानूनी
    0.50
     Они
    0.50
     finance
    0.50
    et
    0.49
     Merino
    0.49
    Activations Density 0.006%

    No Known Activations