© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 49991
    Prev
    Next
    INDEX
    Explanations

    change followed by descriptor

    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
    the
    -1.08
    鷙
    -1.00
    逦
    -0.94
     パイ
    -0.91
    Reached
    -0.90
    INTAIN
    -0.88
    ギュア
    -0.87
    Establish
    -0.87
     スピ
    -0.86
    готавли
    -0.86
    POSITIVE LOGITS
     Change
    1.36
    over
    1.24
    Change
    1.20
     change
    1.18
     detection
    1.15
     wrought
    1.09
    CHANGE
    1.07
    change
    1.06
    变更
    1.05
     diapers
    1.02
    Activations Density 0.042%

    No Known Activations