© 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. 59908
    Prev
    Next
    INDEX
    Explanations

    code delimiters or punctuation

    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
    anni
    -0.75
    ogli
    -0.75
    ruf
    -0.72
     piensa
    -0.71
     servicing
    -0.71
     schnell
    -0.71
     veloce
    -0.69
    norr
    -0.69
     πολι
    -0.69
     Recommended
    -0.69
    POSITIVE LOGITS
    멋
    0.67
     Verne
    0.66
    GRASS
    0.65
    ฐ
    0.64
    ₉
    0.63
    TIPOS
    0.63
     meubles
    0.63
     تحديد
    0.63
    environ
    0.62
    minWidth
    0.62
    Activations Density 0.039%

    No Known Activations