© 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. 34-GEMMASCOPE-RES-131K
    4. 102573
    Prev
    Next
    INDEX
    Explanations

    comments and code structure

    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
     Ива
    -0.73
     finales
    -0.73
     trickle
    -0.71
     domine
    -0.71
     terre
    -0.69
     Yoshida
    -0.69
     Document
    -0.68
    utscher
    -0.68
    StateChanged
    -0.68
     evolutionary
    -0.68
    POSITIVE LOGITS
     funcionando
    0.79
    requirements
    0.76
     principalmente
    0.74
     werken
    0.73
     pesquis
    0.71
    好看
    0.68
     sterility
    0.68
    ujemy
    0.67
    めで
    0.66
    ticello
    0.66
    Activations Density 0.051%

    No Known Activations