© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34762
    Prev
    Next
    INDEX
    Explanations

    problem with

    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
     verantwortlich
    -1.02
     assures
    -1.02
     dismal
    -1.01
     unfailing
    -1.00
    告诉
    -0.99
     importance
    -0.97
    身心
    -0.96
     crucial
    -0.96
     augen
    -0.94
     beteiligt
    -0.91
    POSITIVE LOGITS
     with
    1.51
     too
    1.45
     people
    1.45
     слишком
    1.44
     terlalu
    1.43
     problema
    1.38
     problème
    1.34
    Too
    1.33
     problems
    1.28
    的问题
    1.28
    Activations Density 0.142%

    No Known Activations