© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 129963
    Prev
    Next
    INDEX
    Explanations

    passing through 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
    hopefully
    -1.38
    瑆
    -1.33
     hendes
    -1.33
     sociala
    -1.29
    romas
    -1.27
    despite
    -1.26
    probably
    -1.25
     who
    -1.23
    ㈰
    -1.23
    ﹍﹍
    -1.23
    POSITIVE LOGITS
     at
    1.59
    During
    1.45
    For
    1.34
    After
    1.30
     for
    1.28
     after
    1.23
    When
    1.23
     find
    1.21
     unrelenting
    1.18
     just
    1.17
    Activations Density 0.202%

    No Known Activations