© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63594
    Prev
    Next
    INDEX
    Explanations

    comparative constructions with "as"

    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
    Not in Any Lists

    No Comments

    Negative Logits
     rather
    -1.23
     plutôt
    -1.22
    両方
    -0.97
     Dimen
    -0.93
    rather
    -0.93
    蟷
    -0.91
    (^_^
    -0.91
     pestaña
    -0.89
     représente
    -0.89
     بیشتر
    -0.88
    POSITIVE LOGITS
     a
    1.95
     or
    1.65
     as
    1.52
     an
    1.48
     than
    1.30
     perhaps
    1.05
     now
    1.05
     those
    1.00
     kanske
    0.99
     Maybe
    0.95
    Activations Density 0.018%

    No Known Activations