© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 92278
    Prev
    Next
    INDEX
    Explanations

    common phrases after certain words

    np_acts-logits-general · gemini-2.5-flash-lite

    NP in syntactic trees

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     suelo
    0.53
    бычно
    0.49
     demais
    0.47
     સુધી
    0.47
     ប្រ
    0.46
     estabilidad
    0.45
     જોઈએ
    0.45
    =',
    0.45
    VERNMENT
    0.44
     suelos
    0.44
    POSITIVE LOGITS
     filament
    0.50
    filament
    0.50
     McFadden
    0.47
     McLeod
    0.45
     Filament
    0.45
     McCoy
    0.45
     Milk
    0.44
    bab
    0.44
     Filippo
    0.44
     Barry
    0.43
    Activations Density 0.001%

    No Known Activations