© 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. 32631
    Prev
    Next
    INDEX
    Explanations

    android attributes and file licenses

    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
     REC
    -0.75
    ἃ
    -0.75
     professeur
    -0.75
    QH
    -0.71
     trabajar
    -0.71
     использования
    -0.70
    Dibrom
    -0.69
    MenuGroup
    -0.69
    cích
    -0.69
    ары
    -0.69
    POSITIVE LOGITS
    一方面
    0.75
    Atentamente
    0.65
    Aplicaciones
    0.64
     Entities
    0.63
    mappings
    0.61
     seems
    0.60
     Lenny
    0.60
     Balk
    0.60
    Stacy
    0.59
    widetilde
    0.59
    Activations Density 0.057%

    No Known Activations