© 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. 11491
    Prev
    Next
    INDEX
    Explanations

    introducing a contrast

    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
     therefore
    -1.68
     Encu
    -1.52
    5
    -1.48
     thus
    -1.45
    敺
    -1.39
     to
    -1.36
    これからの
    -1.29
     Artículo
    -1.26
     been
    -1.25
     $\&$
    -1.25
    POSITIVE LOGITS
     nachdem
    1.55
    ꠥ
    1.46
     seguras
    1.46
     after
    1.42
    我们
    1.41
    ﹶ
    1.39
    荩
    1.39
    ciptakan
    1.39
     mega
    1.38
    ଃ
    1.38
    Activations Density 0.006%

    No Known Activations