© 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. 90829
    Prev
    Next
    INDEX
    Explanations

    question marks and punctuation

    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
    9
    -2.33
     incríveis
    -2.11
     comerciais
    -2.09
     internacionais
    -2.09
    通常
    -2.08
     habile
    -2.08
    7
    -2.05
    1
    -2.02
    摃
    -1.94
     originais
    -1.93
    POSITIVE LOGITS
     and
    3.16
     principalmente
    1.77
     alebo
    1.52
     více
    1.51
    ”,
    1.50
     that
    1.48
     concre
    1.48
    丄
    1.47
     anche
    1.45
    ですが
    1.45
    Activations Density 0.032%

    No Known Activations