© 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. 59102
    Prev
    Next
    INDEX
    Explanations

    UI bars

    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
    цион
    -0.96
     dritten
    -0.82
     amerikanischen
    -0.81
    ưu
    -0.78
     они
    -0.77
     э
    -0.77
     réelle
    -0.76
    쉽
    -0.75
    이크
    -0.75
    This
    -0.75
    POSITIVE LOGITS
     Prés
    0.90
     Création
    0.87
     ELEVATION
    0.86
    ⌚
    0.81
     опыта
    0.81
     exces
    0.80
     propiet
    0.78
    🗓
    0.78
     connexions
    0.78
    oot
    0.78
    Activations Density 0.007%

    No Known Activations