© 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. 19402
    Prev
    Next
    INDEX
    Explanations

    conjunctions followed by a pause

    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_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
    f
    -2.25
     is
    -2.14
    s
    -2.06
    ly
    -1.84
     THE
    -1.80
     sogar
    -1.77
    le
    -1.77
    at
    -1.74
     confirms
    -1.70
     universitaria
    -1.67
    POSITIVE LOGITS
    矬
    2.11
    憷
    2.11
    𓄹
    2.05
    anthin
    2.00
    岨
    1.88
    鍆
    1.86
    锖
    1.85
    ція
    1.85
     eradicate
    1.84
    terscotch
    1.82
    Activations Density 0.004%

    No Known Activations