© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 62445
    Prev
    Next
    INDEX
    Explanations

    preposition down

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ા
    -0.75
    一个月
    -0.75
    瀧
    -0.73
    Places
    -0.70
     bildet
    -0.69
    部分は
    -0.68
    Hoo
    -0.68
    方法は
    -0.68
     llevar
    -0.68
    sch
    -0.68
    POSITIVE LOGITS
    payment
    1.05
     Payment
    1.02
     payment
    1.02
     Memory
    1.00
    enumerable
    0.98
     DOWN
    0.97
    sizing
    0.94
     Down
    0.94
     syndrome
    0.93
    Down
    0.91
    Activations Density 0.014%

    No Known Activations