© 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. 102198
    Prev
    Next
    INDEX
    Explanations

    specific nouns followed by modifiers

    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
     zet
    -1.32
     heer
    -1.32
     resultant
    -1.26
     actual
    -1.24
    ially
    -1.20
     treu
    -1.19
    inon
    -1.19
    ,
    -1.16
     wens
    -1.16
    ogues
    -1.16
    POSITIVE LOGITS
     at
    1.89
     from
    1.50
     during
    1.38
    ویژگی
    1.32
     between
    1.30
     къде
    1.27
     variasi
    1.25
     until
    1.23
    沿い
    1.22
     while
    1.21
    Activations Density 1.428%

    No Known Activations