© 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. 60210
    Prev
    Next
    INDEX
    Explanations

    geographic or administrative territory

    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
    鲧
    -2.84
    乁
    -2.06
    😧
    -2.02
     Diputados
    -1.96
     köln
    -1.96
     gethan
    -1.95
    涠
    -1.90
    ꪔ
    -1.90
     サムネイル
    -1.87
     personalización
    -1.85
    POSITIVE LOGITS
     fled
    2.39
    —
    2.36
     neun
    2.34
     sechs
    2.25
     But
    2.17
    但我
    2.17
    :
    2.16
    但他
    2.11
     siete
    2.02
    )-
    1.98
    Activations Density 0.005%

    No Known Activations