© 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. 34-GEMMASCOPE-RES-131K
    7. 79277
    Prev
    Next
    INDEX
    Explanations

    addresses and legal proceedings

    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_34/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
     before
    -0.96
     all
    -0.94
     vaguely
    -0.91
     epitom
    -0.89
     wasps
    -0.87
    </h1>
    -0.84
    !
    -0.83
     expertly
    -0.81
    證明
    -0.79
    <<"\
    -0.79
    POSITIVE LOGITS
     funeral
    1.32
     conster
    1.05
     coffin
    1.05
    Samo
    1.04
    上官
    1.02
    TRIBUN
    0.99
    ANCI
    0.99
    particularly
    0.99
     fidé
    0.99
     mortes
    0.98
    Activations Density 0.002%

    No Known Activations