© 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. 34-GEMMASCOPE-RES-131K
    7. 73686
    Prev
    Next
    INDEX
    Explanations

    wish could

    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_34/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
     unless
    -1.05
     ранее
    -1.03
     ότι
    -1.02
     distintas
    -1.01
    ́c
    -0.99
     весьма
    -0.98
     VERY
    -0.97
     até
    -0.96
     potenciales
    -0.95
     largely
    -0.94
    POSITIVE LOGITS
     more
    1.79
     someday
    1.39
    就好了
    1.19
     every
    1.18
    Every
    1.16
    Just
    1.16
     those
    1.16
    能够
    1.12
     some
    1.09
    Those
    1.09
    Activations Density 0.045%

    No Known Activations