© 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. 11169
    Prev
    Next
    INDEX
    Explanations

    What questions

    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
     probably
    -1.16
    」。
    -1.12
     mainly
    -1.12
    」、
    -1.10
     literally
    -1.09
     usually
    -1.07
     effects
    -1.05
     need
    -1.05
     provide
    -1.04
    ，“
    -1.01
    POSITIVE LOGITS
    1.10
     افتراض
    1.09
    seiti
    1.05
    で一番
    1.04
     offrir
    1.03
     أشهر
    1.03
     deportivas
    1.01
     number
    1.01
     personajes
    1.00
    пление
    1.00
    Activations Density 0.064%

    No Known Activations