© 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. 34-GEMMASCOPE-RES-131K
    7. 81639
    Prev
    Next
    INDEX
    Explanations

    ISO-8859-1

    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_34/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
    Hebrews
    -0.70
     Campo
    -0.67
    tance
    -0.65
    vbo
    -0.65
     uwag
    -0.64
     Ausnahme
    -0.64
     acento
    -0.64
    笞
    -0.63
     получать
    -0.63
    Kni
    -0.63
    POSITIVE LOGITS
    Tec
    0.75
     righe
    0.72
     Tec
    0.70
    REAS
    0.69
    startActivity
    0.69
    LEA
    0.69
    EAT
    0.68
    TEA
    0.68
     SCA
    0.67
    vk
    0.67
    Activations Density 0.048%

    No Known Activations