© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 12174
    Prev
    Next
    INDEX
    Explanations

    Microsoft Surface

    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
     from
    -1.01
     unrelenting
    -0.97
     relatively
    -0.94
     because
    -0.94
     fairly
    -0.91
     tremendously
    -0.91
     ostensibly
    -0.90
     many
    -0.90
     considerably
    -0.89
     on
    -0.88
    POSITIVE LOGITS
    邋
    0.97
    わけです
    0.91
     Ucraina
    0.91
     está
    0.89
     ciertas
    0.89
     rigide
    0.87
    }$\\
    0.87
     اللغة
    0.86
     estaría
    0.85
     sommige
    0.83
    Activations Density 0.000%

    No Known Activations