© 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. 22-GEMMASCOPE-RES-131K
    7. 68987
    Prev
    Next
    INDEX
    Explanations

    building, connecting, measuring, determining

    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
     but
    -1.20
     весьма
    -1.19
     Надо
    -1.14
     éves
    -1.12
     roues
    -1.09
     enkelte
    -1.08
     forthwith
    -1.07
     πρ
    -1.05
     оружи
    -1.03
     således
    -1.03
    POSITIVE LOGITS
    埂
    1.18
    ÄT
    1.17
     cristiana
    1.15
    cookieParser
    1.11
    怎么回事
    1.09
    ⼊
    1.09
     grappling
    1.09
     يت
    1.09
     gradualmente
    1.09
     recieve
    1.08
    Activations Density 0.030%

    No Known Activations