© 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. 119234
    Prev
    Next
    INDEX
    Explanations

    past completed actions

    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
     ולה
    -1.86
     now
    -1.68
     currently
    -1.50
    либо
    -1.34
    现在
    -1.27
     your
    -1.27
    一個
    -1.23
    ING
    -1.16
     akár
    -1.16
    釆
    -1.16
    POSITIVE LOGITS
     lacked
    1.64
     didn
    1.53
     was
    1.48
     oversaw
    1.40
     didnt
    1.39
     grew
    1.39
     took
    1.39
     gave
    1.38
     underwent
    1.29
     withdrew
    1.29
    Activations Density 0.286%

    No Known Activations