© 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. 22-GEMMASCOPE-RES-131K
    7. 128391
    Prev
    Next
    INDEX
    Explanations

    corresponding to properties

    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_22/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
     integers
    -0.83
    🐃
    -0.77
     telefonu
    -0.77
    anthes
    -0.77
     maquilla
    -0.75
    weiten
    -0.75
    το
    -0.75
    帮助
    -0.74
     onlar
    -0.74
    ADDITIONAL
    -0.74
    POSITIVE LOGITS
     corresponding
    3.27
    corresponding
    2.70
     associated
    2.52
     соответству
    2.45
     correspondingly
    2.25
     Corresponding
    2.25
    Corresponding
    2.09
     correspondiente
    2.05
    associated
    2.03
    对应的
    2.03
    Activations Density 0.147%

    No Known Activations