© 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. 73541
    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
    執筆
    -0.93
     executives
    -0.89
    an
    -0.88
     I
    -0.88
    出声
    -0.87
    сам
    -0.85
     our
    -0.84
     p
    -0.84
    года
    -0.84
    énagement
    -0.82
    POSITIVE LOGITS
     diminuer
    1.05
     обслужи
    1.00
    nī
    1.00
    ሠ
    0.99
    嗩
    0.98
     undated
    0.98
     イエ
    0.97
    开始了
    0.97
    Дорогие
    0.96
    ᗯ
    0.94
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.