© 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. 77674
    Prev
    Next
    INDEX
    Explanations

    _UTIL suffix

    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
    wcs
    -0.79
     ARMS
    -0.71
     пі
    -0.71
    ybė
    -0.70
    上位
    -0.69
    Ecological
    -0.68
     Haem
    -0.68
     высоты
    -0.67
     USAGE
    -0.67
     Иванович
    -0.66
    POSITIVE LOGITS
    ahy
    0.90
    うる
    0.78
    цеп
    0.78
    omod
    0.77
     pronouns
    0.75
    acas
    0.74
    MOTION
    0.74
    щихся
    0.73
    オリティ
    0.73
    teinte
    0.72
    Activations Density 0.007%

    No Known Activations