© 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. 3634
    Prev
    Next
    INDEX
    Explanations

    not until

    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
    さじ
    -0.91
    哂
    -0.86
    っており
    -0.86
     ölü
    -0.82
    🚵
    -0.82
     Перед
    -0.81
     литров
    -0.81
    を入れる
    -0.81
     jednou
    -0.81
    久しぶり
    -0.81
    POSITIVE LOGITS
     until
    11.44
    until
    8.44
    Until
    8.06
     Until
    7.56
     jusqu
    7.25
     till
    7.03
    直到
    6.69
     hasta
    6.44
     UNTIL
    6.19
     untill
    5.97
    Activations Density 1.075%

    No Known Activations