© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 102939
    Prev
    Next
    INDEX
    Explanations

    third person plural possessive

    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
     in
    -1.59
     and
    -1.21
     then
    -1.18
    いつも
    -1.17
    你去
    -1.15
    你和
    -1.14
    每个
    -1.13
    Both
    -1.12
     also
    -1.11
     seseorang
    -1.10
    POSITIVE LOGITS
     their
    2.36
     ihrer
    1.68
     їх
    1.51
    给他们
    1.35
    Their
    1.34
    mereka
    1.32
    ják
    1.30
     ihre
    1.30
     منهم
    1.29
    Ꮺ
    1.28
    Activations Density 0.160%

    No Known Activations