© 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. 10-GEMMASCOPE-RES-131K
    7. 104073
    Prev
    Next
    INDEX
    Explanations

    PowerPoint, Word, and documents

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

    the word "PowerPoint" or related presentation software terms.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron strongly activates on occurrences of “PowerPoint” (and related PPT mentions).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    er
    -3.13
    琑
    -2.86
    6
    -2.58
    2
    -2.50
     This
    -2.48
    It
    -2.45
    1
    -2.42
    N
    -2.39
    o
    -2.38
    是
    -2.38
    POSITIVE LOGITS
    泐
    2.86
    塍
    2.53
    齜
    2.44
    튿
    2.41
    ఞ
    2.34
    蟶
    2.31
    合适的
    2.28
     направлении
    2.27
     buchen
    2.27
     organisatie
    2.25
    Activations Density 0.002%

    No Known Activations