© 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. 130593
    Prev
    Next
    INDEX
    Explanations

    when describing changes

    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
     myriad
    -1.11
     wacky
    -1.02
     juſ
    -0.98
     delightfully
    -0.98
     unbelievably
    -0.96
    eav
    -0.94
     REALLY
    -0.94
     ambigu
    -0.93
     élas
    -0.93
     sere
    -0.92
    POSITIVE LOGITS
     during
    2.03
     when
    1.73
     podczas
    1.46
     During
    1.39
     after
    1.34
     before
    1.26
    During
    1.25
    when
    1.15
     accompany
    1.15
     newly
    1.13
    Activations Density 0.226%

    No Known Activations