© 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. 70577
    Prev
    Next
    INDEX
    Explanations

    first person spoken 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
     ـ
    -1.10
     grito
    -1.07
     there
    -0.98
     ⋅
    -0.98
     terras
    -0.98
     semel
    -0.97
     thần
    -0.97
    תיים
    -0.96
     granada
    -0.95
    комплект
    -0.95
    POSITIVE LOGITS
     his
    1.66
     himself
    1.38
     suoi
    1.33
     его
    1.33
     jeśli
    1.15
     seinem
    1.14
    ínu
    1.14
    他的
    1.14
     nuestro
    1.10
     hizo
    1.10
    Activations Density 0.159%

    No Known Activations