© 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. 44704
    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
     [
    -1.03
    mbda
    -0.86
    clyde
    -0.85
     وك
    -0.84
    ，”
    -0.84
    .”)
    -0.83
     комите
    -0.83
    ”:
    -0.83
    };
    -0.83
     deines
    -0.82
    POSITIVE LOGITS
    harap
    0.98
    nsec
    0.96
    的照片
    0.94
    فره
    0.94
     косме
    0.88
     singkat
    0.88
     merciful
    0.88
     försö
    0.86
    éria
    0.84
     Any
    0.84
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.