© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 73358
    Prev
    Next
    INDEX
    Explanations

    beginnings of sentences

    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
    Not in Any Lists

    No Comments

    Negative Logits
     Ebenso
    -0.99
    理石
    -0.96
    imageName
    -0.96
    昨年
    -0.94
    Sự
    -0.93
     лише
    -0.92
     TWO
    -0.90
    梦见
    -0.90
     разные
    -0.90
     tales
    -0.90
    POSITIVE LOGITS
     you
    1.38
     guys
    1.34
     here
    1.34
     today
    1.26
     introducir
    1.16
    prochen
    1.09
     approximately
    1.08
    这里
    1.08
     бю
    1.05
     gonna
    1.03
    Activations Density 0.035%

    No Known Activations