© 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. 199170
    Prev
    Next
    INDEX
    Explanations

    violation of rights

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

    sexually charged and sensitive topics

    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
     gange
    0.47
    രിച്ചി
    0.46
     ausgestattet
    0.45
    ب
    0.44
    Ин
    0.43
    ل
    0.43
     mulig
    0.43
     uten
    0.43
     vær
    0.42
    Д
    0.42
    POSITIVE LOGITS
    可以说
    0.47
     Kamane
    0.46
     મુખ્ય
    0.44
    marital
    0.44
     maliciously
    0.44
     dovet
    0.44
    rVert
    0.42
    নীতির
    0.42
    followlike
    0.42
     columnist
    0.41
    Activations Density 0.001%

    No Known Activations