© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31075
    Prev
    Next
    INDEX
    Explanations

    android open source project

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron detects Android‐related Java package path components (e.g. the “com.google.android.apps.common…” segments).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     salas
    -0.89
     stun
    -0.80
     chế
    -0.79
    訛
    -0.79
    hướng
    -0.75
     Pardon
    -0.74
    •
    -0.74
    ulador
    -0.73
     製作
    -0.72
     überlegen
    -0.72
    POSITIVE LOGITS
    ียด
    0.87
    窃
    0.83
     perdre
    0.83
     savait
    0.77
    呼ば
    0.75
     kırmızı
    0.74
     ALPH
    0.73
    Certainly
    0.73
     nmax
    0.72
    agoza
    0.71
    Activations Density 0.044%

    No Known Activations