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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 70977
    Prev
    Next
    INDEX
    Explanations

    determining whether

    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
     véhicule
    -1.01
     assise
    -0.96
     épouse
    -0.96
    どうして
    -0.94
     télécharge
    -0.92
     brazo
    -0.91
    镜头
    -0.90
     pourtant
    -0.90
     espé
    -0.89
    IZES
    -0.89
    POSITIVE LOGITS
     if
    1.47
     test
    1.13
     whether
    1.05
     by
    1.05
     indicator
    1.01
     observing
    0.99
     through
    0.96
     observe
    0.94
     whose
    0.94
     Indicator
    0.94
    Activations Density 0.173%

    No Known Activations