© 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. 221334
    Prev
    Next
    INDEX
    Explanations

    R. Kelly allegations

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

    actresses and children

    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
    if
    0.54
     ótimo
    0.53
     jeśli
    0.49
    weise
    0.48
    ound
    0.47
     eğer
    0.47
     Если
    0.47
     AppMethodBeat
    0.47
     Я
    0.46
     kalau
    0.46
    POSITIVE LOGITS
    INVALID
    0.44
    TAS
    0.43
    出産
    0.43
    SIAN
    0.42
    탤
    0.42
    DEA
    0.42
     infantil
    0.42
     alcoholism
    0.41
    늙
    0.41
    ベビー
    0.40
    Activations Density 0.006%

    No Known Activations