© 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. 22-GEMMASCOPE-RES-131K
    7. 13031
    Prev
    Next
    INDEX
    Explanations

    adding or completing things

    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
     Assemble
    -0.91
     編集
    -0.84
     Bearbeitung
    -0.77
     Considering
    -0.77
    各个
    -0.75
     Midas
    -0.75
     assembly
    -0.75
     obstacle
    -0.75
     anticipated
    -0.74
    ┛
    -0.73
    POSITIVE LOGITS
     complement
    1.84
     допол
    1.74
     supplementing
    1.72
     zusätzlich
    1.58
     supplement
    1.56
     complementary
    1.52
    complement
    1.48
     complementa
    1.43
     complemento
    1.41
     addition
    1.40
    Activations Density 0.112%

    No Known Activations