© 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. 10-GEMMASCOPE-RES-131K
    7. 119980
    Prev
    Next
    INDEX
    Explanations

    glm, Squid, clump, cabal, arrhythmias

    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_10/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
    狁
    -2.80
    0
    -2.64
    但他
    -2.56
    But
    -2.52
    .
    -2.45
    但是在
    -2.42
     пять
    -2.39
    ”
    -2.38
    但却
    -2.38
     $\
    -2.38
    POSITIVE LOGITS
    埽
    2.84
     wanneer
    2.59
     offrir
    2.42
     uſed
    2.36
     When
    2.31
    还真是
    2.22
    borsa
    2.20
    镦
    2.20
     dengan
    2.17
     知道
    2.17
    Activations Density 0.032%

    No Known Activations