© 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. 293
    Prev
    Next
    INDEX
    Explanations

    days and mornings

    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
    ção
    -1.27
     últimos
    -1.27
     svilupp
    -1.25
    <bos>
    -1.24
     ktorí
    -1.20
     prosegu
    -1.20
    el
    -1.18
    人在
    -1.15
     their
    -1.11
     最終
    -1.11
    POSITIVE LOGITS
     varandra
    1.42
     morning
    1.38
    Our
    1.23
    依照
    1.16
     ladrillo
    1.15
     нашего
    1.14
    分组
    1.13
     ellas
    1.13
     χωρίς
    1.13
    Ƙ
    1.12
    Activations Density 0.030%

    No Known Activations