© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 118439
    Prev
    Next
    INDEX
    Explanations

    either version 2 or later

    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
     twenties
    -1.02
     Compens
    -0.79
    ždy
    -0.79
    rified
    -0.77
     dotyczą
    -0.77
     daudz
    -0.75
    линг
    -0.75
     podjela
    -0.74
    heiser
    -0.73
    Unity
    -0.73
    POSITIVE LOGITS
    ềm
    0.80
     representa
    0.75
    科学家
    0.73
     memoria
    0.71
    size
    0.71
    季节
    0.71
    дых
    0.70
     Dolor
    0.70
     بتاريخ
    0.69
     finalists
    0.69
    Activations Density 0.008%

    No Known Activations