© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 119947
    Prev
    Next
    INDEX
    Explanations

    sentence structure 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
    chê
    -1.46
    ॠ
    -1.42
     have
    -1.41
    ningarna
    -1.41
    INTAIN
    -1.41
     and
    -1.41
     rebajas
    -1.38
     дети
    -1.37
     FIVE
    -1.36
     ehemal
    -1.36
    POSITIVE LOGITS
    :
    1.49
    (
    1.43
    這樣
    1.30
    这样
    1.30
    o
    1.28
     of
    1.22
     italianos
    1.18
    力气
    1.17
     such
    1.16
     as
    1.16
    Activations Density 0.024%

    No Known Activations