© 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. 266
    Prev
    Next
    INDEX
    Explanations

    academy, professor, member, fellow

    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
     to
    -1.75
     that
    -1.47
    说不定
    -1.23
    名叫
    -1.10
    ことなく
    -1.10
     конструкция
    -1.09
     可能
    -1.09
     evtl
    -1.07
    wasan
    -1.06
    /**
    -1.05
    POSITIVE LOGITS
     sinds
    1.33
    isés
    1.24
     melang
    1.19
     войне
    1.16
     gondol
    1.13
    飒
    1.12
     opérés
    1.10
     Fellow
    1.10
    Enemies
    1.09
     essais
    1.09
    Activations Density 0.026%

    No Known Activations