© 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. 47038
    Prev
    Next
    INDEX
    Explanations

    temporary states or objects

    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
    Negative Logits
    เริ่ม
    -1.01
    idiot
    -0.98
     uncompromising
    -0.98
     entrambi
    -0.97
     새로운
    -0.91
     chiunque
    -0.91
    leisure
    -0.91
     qualunque
    -0.91
     terão
    -0.89
    ियर
    -0.88
    POSITIVE LOGITS
     Temporary
    1.50
     temporary
    1.41
    temporary
    1.36
    Temporary
    1.21
    解决方案
    1.18
     increase
    1.09
     use
    1.05
     solucion
    1.05
     tempor
    1.05
     measures
    1.04
    Activations Density 0.029%

    No Known Activations