© 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. 110776
    Prev
    Next
    INDEX
    Explanations

    Copyright notices or license information

    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
    Zheng
    -0.76
    colage
    -0.72
    ffiti
    -0.72
    ា
    -0.72
    Bala
    -0.71
     pareció
    -0.71
     Kenji
    -0.70
     vegetación
    -0.70
     OTHER
    -0.69
    就会
    -0.69
    POSITIVE LOGITS
    У
    0.84
    ş
    0.81
    Twelve
    0.79
     悠
    0.77
    П
    0.72
     Twelve
    0.70
    По
    0.70
    Susan
    0.70
    ส
    0.69
    ancang
    0.68
    Activations Density 0.489%

    No Known Activations