© 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. 22-GEMMASCOPE-RES-131K
    7. 64507
    Prev
    Next
    INDEX
    Explanations

    PWN, KK, CCCC repetition

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     on
    -1.27
     ensures
    -1.21
     undeniably
    -1.18
     publico
    -1.18
     this
    -1.18
     tremendously
    -1.17
     tailored
    -1.16
     Because
    -1.12
     encompasses
    -1.12
     cheerful
    -1.11
    POSITIVE LOGITS
    "> 
    1.26
     dando
    1.21
     pivotal
    1.19
     opulent
    1.15
     ornate
    1.11
    跑去
    1.10
    actually
    1.08
     dinheiro
    1.08
    熟悉的
    1.08
     intric
    1.07
    Activations Density 0.000%

    No Known Activations