© 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. 10-GEMMASCOPE-RES-131K
    7. 67552
    Prev
    Next
    INDEX
    Explanations

    words ending in -ization or -descriptor

    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_10/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
    During
    -1.55
     different
    -1.45
    Several
    -1.45
     тогда
    -1.42
    Very
    -1.41
     very
    -1.41
    Often
    -1.38
     Throughout
    -1.38
     Numerous
    -1.38
     Для
    -1.36
    POSITIVE LOGITS
    itisation
    1.62
     why
    1.57
    opies
    1.44
     znovu
    1.40
     verhind
    1.38
     dê
    1.37
     ۱۵
    1.36
    ฤษ
    1.35
     iesp
    1.34
    itization
    1.34
    Activations Density 0.163%

    No Known Activations