© 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. 60215
    Prev
    Next
    INDEX
    Explanations

    adjectives describing experiences

    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
     still
    -1.80
     kto
    -1.39
     korban
    -1.34
     now
    -1.34
     hiper
    -1.30
     боя
    -1.30
     tez
    -1.30
     bort
    -1.29
     cvi
    -1.27
     naissance
    -1.24
    POSITIVE LOGITS
     since
    1.68
     özellikle
    1.54
     insanların
    1.41
    since
    1.39
     genellikle
    1.38
     lately
    1.33
     nerede
    1.31
     sürekli
    1.30
     aslında
    1.28
     desde
    1.27
    Activations Density 0.115%

    No Known Activations