© 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. 117357
    Prev
    Next
    INDEX
    Explanations

    android components

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

    The neuron fires on occurrences of the literal token “android” in code or import/package names.

    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
    capulco
    -0.96
    шому
    -0.94
     Ero
    -0.89
    eronau
    -0.86
     puerto
    -0.85
     возника
    -0.75
     octavo
    -0.75
     Verv
    -0.75
     själva
    -0.74
     Requis
    -0.74
    POSITIVE LOGITS
     nadzie
    0.87
     miesią
    0.87
    兎
    0.84
    解释
    0.84
     кстати
    0.78
    Something
    0.77
    楽しめます
    0.77
     Diskussion
    0.75
     Kerja
    0.75
     Gesetze
    0.75
    Activations Density 0.015%

    No Known Activations