© 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. 92812
    Prev
    Next
    INDEX
    Explanations

    android package names

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

    The neuron fires on dotted “reverse‐domain” or package‐style identifiers (e.g. com.apple.InterfaceBuilder3.CocoaTouch.Storyboard or com.google.android.maps).

    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
     связь
    -0.94
     смысл
    -0.87
    letoe
    -0.83
    late
    -0.82
     мысль
    -0.80
    lorum
    -0.80
     and
    -0.79
    cades
    -0.79
    strum
    -0.78
    stris
    -0.78
    POSITIVE LOGITS
    しても
    1.10
     Apabila
    0.98
     jste
    0.98
    
    0.96
     Bahkan
    0.95
     Sementara
    0.95
    椋
    0.95
     Bentuk
    0.93
     reiv
    0.92
    Zitat
    0.91
    Activations Density 0.042%

    No Known Activations