© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 66285
    Prev
    Next
    INDEX
    Explanations

    passing data using intents

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

    The neuron is spotting Intent extra keys or constant names used when calling putExtra/getExtra in Android code.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     vivió
    -1.11
    estors
    -1.10
     vores
    -1.08
    politan
    -1.07
    january
    -1.05
    represents
    -1.05
    ыр
    -1.04
     leven
    -1.03
    fotografia
    -1.03
     sospe
    -1.02
    POSITIVE LOGITS
    k
    1.05
    PARAM
    1.02
    1
    0.97
     нужно
    0.94
     переда
    0.94
     time
    0.93
    arg
    0.93
     from
    0.91
     information
    0.90
    name
    0.88
    Activations Density 0.002%

    No Known Activations