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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 48107
    Prev
    Next
    INDEX
    Explanations

    asking questions and for items

    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
     процессе
    -0.79
     sientes
    -0.77
     wiele
    -0.74
     CURIAM
    -0.73
     workshops
    -0.72
    platz
    -0.72
     Final
    -0.71
     determined
    -0.71
     various
    -0.70
    ковые
    -0.70
    POSITIVE LOGITS
     questions
    1.16
    questions
    1.10
    attempt
    1.08
     perguntas
    0.97
     preguntas
    0.96
    Questions
    0.95
    atility
    0.94
    Answer
    0.94
    Attempt
    0.94
    SECTION
    0.93
    Activations Density 0.007%

    No Known Activations