© 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. 10-GEMMASCOPE-RES-131K
    7. 65789
    Prev
    Next
    INDEX
    Explanations

    power generation and electricity

    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_10/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
    又一次
    -1.41
    羂
    -1.38
    Popularity
    -1.30
     mismos
    -1.23
    ]+"
    -1.20
    皝
    -1.18
     Smarter
    -1.16
    Criter
    -1.16
     Bonuses
    -1.16
    sipkan
    -1.15
    POSITIVE LOGITS
    1.30
    🌞
    1.28
     example
    1.16
     Архивировано
    1.16
     well
    1.15
     true
    1.13
     particular
    1.13
     Februar
    1.13
     initial
    1.13
     about
    1.13
    Activations Density 0.087%

    No Known Activations