© 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. 73495
    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
     oversize
    -1.02
    Jangan
    -1.00
    PRACT
    -0.98
    número
    -0.98
    Libert
    -0.96
    Collaborative
    -0.96
    いいのか
    -0.95
    mbalikan
    -0.94
    tarta
    -0.91
    menü
    -0.91
    POSITIVE LOGITS
     Hwy
    1.01
    ㅜ
    1.00
    𝑦
    0.98
    So
    0.97
    ㅕ
    0.96
    ॥
    0.94
    。
    0.93
     FEBRUARY
    0.91
     Briefe
    0.90
    Nm
    0.90
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.