© 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. 3400
    Prev
    Next
    INDEX
    Explanations

    passive voice events

    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
     from
    -1.25
     to
    -1.16
    感じる
    -0.92
     through
    -0.86
    ophone
    -0.84
     scientifically
    -0.82
     having
    -0.80
    ผ่าน
    -0.80
     of
    -0.77
     that
    -0.75
    POSITIVE LOGITS
     by
    1.08
     всеми
    1.05
    joyed
    0.88
    噌
    0.87
     appelée
    0.85
    crossed
    0.84
    Iq
    0.84
    accessed
    0.83
    gså
    0.82
     усі
    0.82
    Activations Density 0.081%

    No Known Activations