© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30368
    Prev
    Next
    INDEX
    Explanations

    ignoring or omitting facts

    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
     in
    -0.90
    🌌
    -0.89
     максимально
    -0.87
     различные
    -0.84
     разных
    -0.82
    当时的
    -0.82
    sih
    -0.81
     innan
    -0.81
     įva
    -0.81
    جات
    -0.81
    POSITIVE LOGITS
     obvious
    2.52
    obvious
    1.93
     important
    1.69
     evidence
    1.62
     crucial
    1.61
    Clearly
    1.54
     facts
    1.51
     clearly
    1.46
     оче
    1.37
    Obviously
    1.37
    Activations Density 0.057%

    No Known Activations