© 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. 34-GEMMASCOPE-RES-131K
    7. 107637
    Prev
    Next
    INDEX
    Explanations

    transition or concluding phrases

    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_34/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
     there
    -1.23
    ☺️
    -1.04
    WHERE
    -1.04
    👍🏻
    -1.01
    ♥️
    -0.98
     بسیاری
    -0.96
     immédiatement
    -0.93
    ｄ
    -0.93
     vieles
    -0.89
    izacin
    -0.89
    POSITIVE LOGITS
     Anyway
    1.75
     besides
    1.69
     Besides
    1.59
     anyway
    1.59
     anyhow
    1.52
    Anyway
    1.48
     beside
    1.41
     concerning
    1.41
     Beside
    1.38
     regarding
    1.37
    Activations Density 0.137%

    No Known Activations