© 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. 67255
    Prev
    Next
    INDEX
    Explanations

    short answer 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
     vende
    -1.08
     biblia
    -1.02
     kutu
    -0.99
    atischen
    -0.94
    illige
    -0.94
    HEARING
    -0.94
     MEMBER
    -0.93
    NOWLEDG
    -0.93
    formatics
    -0.93
     教程
    -0.93
    POSITIVE LOGITS
     These
    1.27
     you
    1.23
     these
    1.20
     essas
    1.17
     your
    1.13
    These
    1.09
     эти
    1.06
     estos
    1.05
    これらの
    1.03
     gelangt
    1.03
    Activations Density 0.007%

    No Known Activations