© 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. 3422
    Prev
    Next
    INDEX
    Explanations

    acting preparation

    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
     السياس
    -0.92
     aufgebaut
    -0.81
    jarat
    -0.81
    ция
    -0.81
    Ԁ
    -0.80
     rumahnya
    -0.79
     seguirá
    -0.78
    ā
    -0.78
    Today
    -0.76
     Heute
    -0.76
    POSITIVE LOGITS
     acting
    1.58
     character
    1.41
     actors
    1.38
     preparation
    1.35
     Actors
    1.30
     rehearsals
    1.29
     подготов
    1.27
    Preparation
    1.24
    Actors
    1.23
     improvis
    1.21
    Activations Density 0.019%

    No Known Activations