© 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. 10-GEMMASCOPE-RES-131K
    7. 15473
    Prev
    Next
    INDEX
    Explanations

    numbers like 2, 3, 4

    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
     verändert
    -1.18
    demies
    -1.15
    s
    -1.13
    同事
    -1.13
    Kapp
    -1.12
    pozycji
    -1.11
     instrucción
    -1.10
    忐
    -1.10
     vermogen
    -1.10
    ultas
    -1.10
    POSITIVE LOGITS
     continuar
    1.35
     宣传
    1.34
    They
    1.29
    낀
    1.13
     autonomie
    1.13
     was
    1.12
    
    1.09
     They
    1.07
     быть
    1.06
     prosegu
    1.05
    Activations Density 0.178%

    No Known Activations