© 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. 47761
    Prev
    Next
    INDEX
    Explanations

    passage of time

    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
     now
    -1.94
     some
    -1.67
     seen
    -1.45
     yesterday
    -1.41
     made
    -1.40
     including
    -1.37
     using
    -1.34
     many
    -1.30
     kept
    -1.30
     caused
    -1.30
    POSITIVE LOGITS
    skrä
    1.42
    ผม
    1.40
    我们的
    1.32
    发布时间
    1.20
     azonban
    1.20
    Laos
    1.19
    ของ
    1.19
    เรา
    1.18
     了
    1.17
    اگر
    1.16
    Activations Density 0.036%

    No Known Activations