© 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. 73670
    Prev
    Next
    INDEX
    Explanations

    paste special

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron fires on occurrences of the word “paste” (or its form “pasted”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    ’
    -2.95
     This
    -2.89
    ‘
    -2.58
    ان
    -2.48
    但是在
    -2.39
     —
    -2.33
     are
    -2.27
     beispiel
    -2.22
    但在
    -2.22
     paired
    -2.20
    POSITIVE LOGITS
    ↵
    3.38
     Когда
    2.80
     When
    2.61
    Responding
    2.39
    Regarding
    2.28
     quand
    2.25
     centerpiece
    2.25
     когда
    2.25
     dasarnya
    2.22
    Luckily
    2.19
    Activations Density 0.005%

    No Known Activations