© 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. 81030
    Prev
    Next
    INDEX
    Explanations

    for loops and variables

    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
     когда
    -1.16
    IconModule
    -0.99
     however
    -0.99
    arquia
    -0.92
     zl
    -0.88
    ⠰
    -0.88
     Émile
    -0.86
     reft
    -0.85
     zdan
    -0.85
     Că
    -0.84
    POSITIVE LOGITS
     =
    1.60
    =
    1.57
     sake
    1.11
    Iterator
    1.05
     :
    1.01
     varandra
    1.00
    iterator
    0.99
     gånger
    0.96
    ループ
    0.93
     veck
    0.92
    Activations Density 0.014%

    No Known Activations