© 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. 36173
    Prev
    Next
    INDEX
    Explanations

    n and m variables

    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
    禰
    -1.28
     some
    -1.23
     on
    -1.23
    หรือ
    -1.17
     during
    -1.16
     while
    -1.13
     after
    -1.13
    …！
    -1.11
     both
    -1.10
    や
    -1.09
    POSITIVE LOGITS
    為に
    1.21
    さき
    1.19
     Provides
    1.11
     municipale
    1.09
    Добавлено
    1.08
    perhaps
    1.07
     Coordin
    1.05
     इसकी
    1.04
     Dinas
    1.03
    
    1.02
    Activations Density 0.024%

    No Known Activations