© 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. 71217
    Prev
    Next
    INDEX
    Explanations

    pronoun followed by verb

    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
    //}
    -1.41
    -
    -1.35
     یکی
    -1.34
    Tierra
    -1.34
     is
    -1.30
     sèche
    -1.30
     jsou
    -1.28
    Siapa
    -1.27
    Waff
    -1.27
    Sied
    -1.27
    POSITIVE LOGITS
     we
    2.28
     that
    1.66
     vetorial
    1.60
     parec
    1.51
     obtain
    1.40
     wszystkie
    1.38
     możemy
    1.38
     noin
    1.36
     całą
    1.35
     $
    1.32
    Activations Density 0.069%

    No Known Activations