© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8762
    Prev
    Next
    INDEX
    Explanations

    suite of

    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
    但
    -1.46
    .
    -1.37
     моего
    -1.34
    b
    -1.30
     on
    -1.27
    我们的
    -1.26
    it
    -1.23
     “
    -1.20
    。」
    -1.19
    通過
    -1.19
    POSITIVE LOGITS
     of
    2.06
     freaking
    1.56
     cristianos
    1.55
     тот
    1.47
    >
    1.47
    沨
    1.45
     that
    1.45
     oscu
    1.41
     conocer
    1.39
     غذایی
    1.38
    Activations Density 0.054%

    No Known Activations