© 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. 87026
    Prev
    Next
    INDEX
    Explanations

    code file operations

    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
     do
    -2.36
    do
    -2.17
     Do
    -1.52
     DO
    -1.48
    Do
    -1.41
     dos
    -1.38
    dos
    -1.36
    DO
    -1.30
     до
    -1.13
     doo
    -1.07
    POSITIVE LOGITS
     encant
    0.84
     naturais
    0.81
    t
    0.81
     着用
    0.80
     digitais
    0.79
    jahres
    0.75
    ﹢
    0.75
    0.75
    lwjgl
    0.75
     Graves
    0.75
    Activations Density 0.016%

    No Known Activations