© 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. 19596
    Prev
    Next
    INDEX
    Explanations

    an or an followed by a noun

    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
     if
    -1.59
     also
    -1.52
    owią
    -1.44
     ส์
    -1.38
    がありますが
    -1.34
     něk
    -1.34
    鋮
    -1.34
    сль
    -1.31
    also
    -1.30
    fillment
    -1.30
    POSITIVE LOGITS
     như
    1.54
    :
    1.41
     such
    1.29
     сериала
    1.28
     систему
    1.24
    d
    1.23
     chúng
    1.22
     seperti
    1.20
     accepter
    1.18
    ntesis
    1.17
    Activations Density 0.493%

    No Known Activations