© 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. 67693
    Prev
    Next
    INDEX
    Explanations

    action or state completion

    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
    だが
    -1.24
    そして
    -1.09
     (!)
    -1.06
     Ramadhan
    -1.05
     preocup
    -1.04
     از
    -1.04
    Fonto
    -1.03
    ></
    -1.02
    ALLY
    -1.00
     (“
    -1.00
    POSITIVE LOGITS
     escribiendo
    1.21
     in
    1.18
    paquete
    1.16
     apoya
    1.15
    cyclopedia
    1.13
    츄
    1.13
     enchufe
    1.13
    appartamento
    1.12
    玙
    1.11
    えています
    1.10
    Activations Density 0.020%

    No Known Activations