© 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. 21600
    Prev
    Next
    INDEX
    Explanations

    "Yo" as an interjection or at start of names

    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
    <td>
    -2.86
    i
    -2.77
    which
    -2.72
    赜
    -2.69
     And
    -2.63
     небольшой
    -2.59
     และ
    -2.50
    ágenes
    -2.48
     täglichen
    -2.47
    they
    -2.45
    POSITIVE LOGITS
    It
    2.84
    To
    2.83
    𝄆
    2.58
    The
    2.55
    😿
    2.39
    硨
    2.33
    紅色
    2.25
    ᠌
    2.25
     extérieure
    2.23
     intellectuelle
    2.23
    Activations Density 0.002%

    No Known Activations