© 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. 78471
    Prev
    Next
    INDEX
    Explanations

    AppCompatActivity imports and Android code

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

    The neuron is picking up AndroidX import/package tokens (especially the dots and identifiers in androidx.* import lines).

    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
    şme
    -0.86
     OBITUARY
    -0.85
    vains
    -0.84
    ariums
    -0.81
    lutning
    -0.79
    ࣭
    -0.79
     ObjectMapper
    -0.78
    lst
    -0.77
     проє
    -0.76
    bonded
    -0.75
    POSITIVE LOGITS
    appcompat
    1.24
    AppCompat
    0.94
     AppCompat
    0.93
    setContentView
    0.92
     androidx
    0.86
     nyug
    0.82
     suppor
    0.78
     asemenea
    0.77
     vee
    0.77
     agric
    0.76
    Activations Density 0.003%

    No Known Activations