© 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. 34-GEMMASCOPE-RES-131K
    7. 57446
    Prev
    Next
    INDEX
    Explanations

    java class definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    SBATCH
    -0.94
    ђа
    -0.89
    emat
    -0.82
     matang
    -0.80
     Væ
    -0.80
     `${
    -0.79
    ℅
    -0.78
    queryInterface
    -0.78
    ワイイ
    -0.78
    ("../
    -0.77
    POSITIVE LOGITS
    atel
    0.86
     ネック
    0.84
    final
    0.82
    со
    0.81
     final
    0.81
    ]()
    0.81
     предлага
    0.80
     sprawd
    0.80
    util
    0.79
     probablement
    0.79
    Activations Density 0.011%

    No Known Activations