© 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. 11233
    Prev
    Next
    INDEX
    Explanations

    ISBN numbers and questions

    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
    なんだけど
    -1.24
     kjem
    -1.16
     tilgjenge
    -1.13
    ¹)
    -1.12
    openzeppelin
    -1.11
     vakantie
    -1.10
    の準備
    -1.09
     asla
    -1.08
     mennesker
    -1.08
    cepción
    -1.08
    POSITIVE LOGITS
    g
    1.18
     these
    1.06
    Vorte
    1.02
    と
    1.01
     could
    0.98
    8
    0.98
     Khusus
    0.96
     anbieten
    0.94
     sucess
    0.94
     Lakukan
    0.94
    Activations Density 0.002%

    No Known Activations