© 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. 33890
    Prev
    Next
    INDEX
    Explanations

    completion by date

    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
     begins
    -1.20
     starts
    -1.17
    beginTransaction
    -1.09
     start
    -1.07
     to
    -1.05
    Starting
    -1.00
    事情
    -1.00
     began
    -0.99
     more
    -0.99
     Aktivitäten
    -0.98
    POSITIVE LOGITS
     completion
    1.13
     finalmente
    1.03
    年底
    1.02
     finish
    1.01
     by
    1.00
    argout
    0.98
     complet
    0.97
    终于
    0.97
     duong
    0.94
     Completion
    0.94
    Activations Density 0.043%

    No Known Activations