© 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. 38518
    Prev
    Next
    INDEX
    Explanations

    action completed successfully

    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
    ruka
    -1.38
    recently
    -1.22
    onlu
    -1.16
    愀
    -1.16
    provides
    -1.15
    athered
    -1.13
    happened
    -1.12
     ständig
    -1.10
     komplet
    -1.10
    sä
    -1.09
    POSITIVE LOGITS
     has
    2.83
     successfully
    2.28
     was
    2.20
     is
    1.86
     added
    1.73
     been
    1.66
     berhasil
    1.57
     успешно
    1.55
     telah
    1.51
     đã
    1.46
    Activations Density 0.025%

    No Known Activations