© 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. 39569
    Prev
    Next
    INDEX
    Explanations

    religious or celebratory events

    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
     type
    -1.48
     there
    -1.31
     see
    -1.30
     can
    -1.30
    )
    -1.28
    ◔
    -1.22
     haberse
    -1.20
    見えます
    -1.20
     acidente
    -1.20
     perigo
    -1.18
    POSITIVE LOGITS
     the
    1.59
    consulté
    1.52
    ナイキ
    1.30
    撰文
    1.29
    こんばん
    1.27
    Penulis
    1.25
    Erstellt
    1.23
    ６
    1.23
     vocale
    1.23
     francès
    1.23
    Activations Density 0.055%

    No Known Activations