© 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. 86296
    Prev
    Next
    INDEX
    Explanations

    they/their/its

    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
     a
    -1.41
     such
    -1.35
     informé
    -1.25
     împre
    -1.21
     bestanden
    -1.18
    Библи
    -1.13
     vermel
    -1.13
     deose
    -1.12
     manches
    -1.10
     asemenea
    -1.09
    POSITIVE LOGITS
     őket
    1.71
     they
    1.57
    裨
    1.53
     они
    1.50
     their
    1.46
     They
    1.41
     THEY
    1.41
    啻
    1.40
    他们
    1.38
     их
    1.37
    Activations Density 0.130%

    No Known Activations