© 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. 130138
    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
     and
    -1.17
    !”
    -1.05
    寬
    -1.03
     unusually
    -0.96
     komunikasi
    -0.93
     started
    -0.93
     both
    -0.93
    潇
    -0.93
     Brasile
    -0.93
     acad
    -0.92
    POSITIVE LOGITS
     angefü
    1.05
     jolt
    1.04
    崇拜
    1.03
    Transcrip
    0.98
    atically
    0.98
     caress
    0.96
     variés
    0.93
    빽
    0.93
     lápis
    0.93
     оставля
    0.92
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.