© 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. 34-GEMMASCOPE-RES-131K
    7. 108702
    Prev
    Next
    INDEX
    Explanations

    explaining problems and solutions

    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
    ällning
    -1.00
    inverno
    -0.96
    rijving
    -0.95
    CEEDED
    -0.95
    ülerin
    -0.93
    Олег
    -0.93
    Übersetzung
    -0.92
    🚟
    -0.91
    pellier
    -0.91
     rígida
    -0.90
    POSITIVE LOGITS
    就是
    2.80
    คือ
    2.56
     is
    2.53
    的就是
    2.36
     就是
    2.09
    的是
    2.03
    のは
    1.79
    それは
    1.72
     yaitu
    1.68
     คือ
    1.66
    Activations Density 0.024%

    No Known Activations