© 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. 116932
    Prev
    Next
    INDEX
    Explanations

    arithmetic operations including addition

    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
    を選択します
    -1.12
    cioni
    -1.06
    värr
    -1.02
    kách
    -1.00
    くれ
    -1.00
    ที
    -0.94
    prehension
    -0.92
    ⸃
    -0.92
    irdre
    -0.88
    minus
    -0.88
    POSITIVE LOGITS
    加上
    1.57
     +
    1.48
     addition
    1.41
     lisäksi
    1.41
     además
    1.35
    Además
    1.30
     combined
    1.28
     плюс
    1.28
     plus
    1.27
     added
    1.27
    Activations Density 0.122%

    No Known Activations