© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 71725
    Prev
    Next
    INDEX
    Explanations

    months and days

    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
     a
    -1.64
     malé
    -1.48
     coração
    -1.41
     biela
    -1.36
     músico
    -1.32
    mvh
    -1.27
     tampaknya
    -1.26
    WERS
    -1.25
     srdce
    -1.24
     skoro
    -1.22
    POSITIVE LOGITS
     and
    1.40
    Similarly
    1.34
     चीज़
    1.24
     of
    1.20
     „
    1.19
    логических
    1.16
    「
    1.14
    /
    1.13
     bren
    1.12
     ホテル
    1.10
    Activations Density 0.352%

    No Known Activations