© 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. 13785
    Prev
    Next
    INDEX
    Explanations

    legal case context

    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
     version
    -1.12
     Talvez
    -1.10
    וּ
    -1.09
     Química
    -1.08
     Início
    -1.07
    ᾿
    -1.03
     ocurrir
    -1.02
     Uniwers
    -1.01
    無し
    -0.99
     Japão
    -0.99
    POSITIVE LOGITS
     stärken
    1.24
    вится
    1.20
     прокура
    1.19
    🧫
    1.18
    ֹת
    1.15
    ׇ
    1.13
     angem
    1.10
    ellants
    1.09
     сезон
    1.08
     régal
    1.08
    Activations Density 0.000%

    No Known Activations