© 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. 65158
    Prev
    Next
    INDEX
    Explanations

    device storage and memory

    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
    erías
    -0.83
    dymo
    -0.82
     encantado
    -0.77
    xtext
    -0.76
    NFPA
    -0.76
     آم
    -0.76
    
    -0.75
    QtGui
    -0.74
     colección
    -0.73
     tiras
    -0.73
    POSITIVE LOGITS
     storage
    2.97
     memory
    2.23
    storage
    2.19
    Storage
    2.13
     Storage
    2.11
    STORAGE
    1.98
     STORAGE
    1.90
    存储
    1.66
    getStorage
    1.60
     almacenamiento
    1.57
    Activations Density 0.045%

    No Known Activations