© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 66810
    Prev
    Next
    INDEX
    Explanations

    names starting with Pat

    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
    </h3>
    -2.98
     are
    -2.75
    ありますが
    -2.53
     ,"
    -2.27
    tedrale
    -2.25
     indulging
    -2.25
    .\\
    -2.17
     generan
    -2.17
    <em>
    -2.17
     for
    -2.11
    POSITIVE LOGITS
    6
    3.13
    </b>
    2.80
    已經
    2.77
    2
    2.64
    们的
    2.61
    3
    2.58
    饪
    2.53
    無法
    2.52
    1
    2.48
    4
    2.48
    Activations Density 0.007%

    No Known Activations