© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12315
    Prev
    Next
    INDEX
    Explanations

    Eureka! or Q: question prompts

    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
     because
    -2.30
     before
    -2.05
     despite
    -2.03
     on
    -2.03
    ！(
    -1.98
     in
    -1.93
     from
    -1.88
     does
    -1.88
     which
    -1.87
     have
    -1.83
    POSITIVE LOGITS
    すっ
    2.11
     magnificent
    2.05
     marvelous
    2.03
     gigantic
    2.02
     myriad
    1.94
     ridiculously
    1.94
     idiotic
    1.87
     crappy
    1.86
     insanely
    1.86
     splendid
    1.84
    Activations Density 0.000%

    No Known Activations