© 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. 15306
    Prev
    Next
    INDEX
    Explanations

    mathematical variable 'a'

    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
     nell
    -1.19
    。
    -1.16
    émica
    -1.13
    涸
    -1.06
     nel
    -1.06
     restos
    -1.05
    ¹)
    -1.04
    CLING
    -1.04
     to
    -1.03
    さを
    -1.03
    POSITIVE LOGITS
     acrí
    1.30
     meisten
    1.19
     Hinblick
    1.17
     neuesten
    1.15
     grossen
    1.09
    écoute
    1.07
    Quelles
    1.05
    ailleurs
    1.05
    7
    1.02
     dritte
    1.02
    Activations Density 0.044%

    No Known Activations