© 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. 71115
    Prev
    Next
    INDEX
    Explanations

    have + preposition

    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
     myös
    -2.34
    Интере
    -2.33
    Хороший
    -2.22
    Hanya
    -2.14
    Tentang
    -2.14
     énorme
    -2.11
     oreille
    -2.11
    Ако
    -2.08
    魠
    -2.06
     mikina
    -2.05
    POSITIVE LOGITS
     to
    3.70
     in
    2.91
     on
    2.64
     that
    2.44
     as
    2.17
     In
    2.16
     with
    2.06
     they
    2.03
     at
    1.96
     At
    1.91
    Activations Density 0.024%

    No Known Activations