© 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. 64355
    Prev
    Next
    INDEX
    Explanations

    inform and warn

    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
    #%%
    -0.94
     dificil
    -0.93
    kmäler
    -0.92
     mercen
    -0.91
    ##
    -0.87
     ceder
    -0.86
     fero
    -0.85
    estacks
    -0.85
     derni
    -0.84
     hecta
    -0.84
    POSITIVE LOGITS
     information
    1.52
     disclosure
    1.33
     inform
    1.30
     notify
    1.26
     notification
    1.16
     warn
    1.13
     informing
    1.13
     اطلاع
    1.12
     about
    1.10
     информация
    1.06
    Activations Density 0.030%

    No Known Activations