© 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. 16655
    Prev
    Next
    INDEX
    Explanations

    exclamations of strong opinion

    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
    ヤバ
    -1.22
     redonda
    -1.14
     molti
    -1.09
     BECAUSE
    -1.05
     molte
    -1.05
     taşlı
    -1.02
    して下さい
    -1.02
     aislada
    -1.02
    ご了承ください
    -1.02
     angustia
    -1.01
    POSITIVE LOGITS
    !
    3.00
    ！
    1.88
    !!
    1.65
    !”
    1.55
     this
    1.48
    !!!
    1.45
    !"
    1.35
    !
    1.31
    !!!!
    1.27
     !
    1.27
    Activations Density 0.020%

    No Known Activations