© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 71328
    Prev
    Next
    INDEX
    Explanations

    syntax and code tokens

    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
     aici
    -1.15
     quidem
    -1.13
    ungkin
    -1.09
    쨩
    -1.08
    jsko
    -1.07
    城的
    -1.07
     ejemplos
    -1.06
    ╒
    -1.06
    typically
    -1.05
     neque
    -1.05
    POSITIVE LOGITS
     then
    1.37
    Źródło
    1.14
    Endereço
    1.12
    }.
    
    1.11
     and
    1.11
     esmalte
    1.10
    CCIÓN
    1.06
     katholischen
    1.05
    aumento
    1.05
    bước
    1.05
    Activations Density 0.023%

    No Known Activations