© 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. 21063
    Prev
    Next
    INDEX
    Explanations

    node

    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
    .
    -2.25
    e
    -1.88
    0
    -1.84
     vorigen
    -1.83
    o
    -1.71
    .”
    -1.66
    3
    -1.58
    5
    -1.57
    しました
    -1.49
    6
    -1.49
    POSITIVE LOGITS
    \
    1.96
     cív
    1.95
    笕
    1.93
    翆
    1.92
    guigu
    1.90
     asesino
    1.90
    诞生
    1.88
     fotógrafo
    1.87
    情報を
    1.87
     grito
    1.86
    Activations Density 0.041%

    No Known Activations