© 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. 7781
    Prev
    Next
    INDEX
    Explanations

    XML tags

    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
    unpublished
    -1.79
     AND
    -1.78
    ⮑
    -1.77
    缓缓
    -1.75
    となる
    -1.74
     relativamente
    -1.74
     şeyi
    -1.73
     choisi
    -1.73
    IQR
    -1.72
    ⬈
    -1.71
    POSITIVE LOGITS
    2
    2.77
    7
    2.58
    3
    2.56
    1
    2.42
    5
    2.42
    4
    2.38
    There
    2.16
    You
    2.13
    6
    2.03
     if
    2.00
    Activations Density 0.006%

    No Known Activations