© 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. 10-GEMMASCOPE-RES-131K
    7. 128103
    Prev
    Next
    INDEX
    Explanations

    adverbs of probability or certainty

    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
     every
    -1.80
     as
    -1.68
     EVERY
    -1.59
     each
    -1.58
     such
    -1.54
     JUST
    -1.46
     after
    -1.42
     one
    -1.39
     until
    -1.38
     Every
    -1.38
    POSITIVE LOGITS
     utilisé
    1.39
     différentes
    1.36
     않았
    1.35
     边框
    1.30
     rapidement
    1.27
     можем
    1.26
    も見
    1.26
     lorsqu
    1.25
     diversos
    1.23
    タコ
    1.23
    Activations Density 0.097%

    No Known Activations