© 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. 73297
    Prev
    Next
    INDEX
    Explanations

    android ipc protocols

    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
     газо
    -0.74
     حسین
    -0.71
    (!(
    -0.69
    Koala
    -0.68
    ILY
    -0.67
    дение
    -0.66
    venty
    -0.66
     Perspek
    -0.65
    òa
    -0.65
     中山
    -0.65
    POSITIVE LOGITS
     Binder
    1.26
     binder
    1.20
     IPC
    1.16
    Bundle
    1.01
     IB
    0.97
    IPC
    0.95
     Bundle
    0.90
    IBinder
    0.90
    binder
    0.89
    Messenger
    0.89
    Activations Density 0.031%

    No Known Activations