© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 22526
    Prev
    Next
    INDEX
    Explanations

    Planned Parenthood and other plans

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     この
    -2.91
    的变化
    -2.59
    ⃙
    -2.58
    ☆☆☆☆
    -2.30
     když
    -2.28
     当
    -2.27
     これ
    -2.25
    ções
    -2.25
    VIATIONS
    -2.25
     Efek
    -2.23
    POSITIVE LOGITS
    亊
    3.03
    li
    3.02
    as
    2.75
    U
    2.61
    .
    2.59
    "
    2.59
    ൎ
    2.56
     he
    2.53
     planned
    2.50
    an
    2.48
    Activations Density 0.003%

    No Known Activations