© 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. 13005
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Gentile
    -1.12
    Сколько
    -1.09
    お疲れ
    -1.09
     што
    -1.09
    Spesifikasi
    -1.07
    Tujuan
    -1.04
    Semua
    -1.03
    Baik
    -1.02
     برای
    -1.01
    ไหน
    -1.01
    POSITIVE LOGITS
     andere
    1.32
    arraycopy
    1.29
     hundert
    1.21
     sê
    1.20
    ја
    1.20
     of
    1.18
     diharapkan
    1.17
     стоко
    1.16
     hormigón
    1.16
     dê
    1.15
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.