© 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. 34-GEMMASCOPE-RES-131K
    7. 91882
    Prev
    Next
    INDEX
    Explanations

    http:// or this

    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_34/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
     hinzugefügt
    -1.01
    rfan
    -0.99
     alleges
    -0.97
    pherds
    -0.96
     kuchen
    -0.96
    лся
    -0.94
     hodiny
    -0.94
     appelé
    -0.93
    nadequate
    -0.92
    jelaskan
    -0.92
    POSITIVE LOGITS
     this
    1.93
    this
    1.34
     dieser
    1.11
     этого
    1.05
     cette
    1.03
     initialize
    1.02
     questa
    1.01
     its
    1.00
     iniz
    0.99
    افر
    0.96
    Activations Density 0.010%

    No Known Activations