© 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. 87184
    Prev
    Next
    INDEX
    Explanations

    quotes after speech verbs

    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
     who
    -1.83
     with
    -1.72
     it
    -1.67
     had
    -1.59
     showed
    -1.57
     aimed
    -1.56
     gave
    -1.54
     appeared
    -1.52
     became
    -1.52
     took
    -1.51
    POSITIVE LOGITS
     extremadamente
    1.54
     inférieur
    1.47
     rús
    1.45
    先是
    1.43
     例
    1.42
     associée
    1.40
     которое
    1.40
     göm
    1.38
     referirse
    1.38
     conducir
    1.37
    Activations Density 0.015%

    No Known Activations