© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 98711
    Prev
    Next
    INDEX
    Explanations

    Android Bundle class

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

    The neuron strongly activates whenever the token “Bundle” appears (especially in Android import/use of android.os.Bundle).

    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
    '
    -1.33
    el
    -1.33
     not
    -1.28
     certain
    -1.15
    an
    -1.13
     your
    -1.08
     my
    -1.07
    现在的
    -1.07
    ar
    -1.04
     most
    -1.04
    POSITIVE LOGITS
     récol
    1.23
     olabilir
    1.21
     contrô
    1.15
    unno
    1.13
    ronic
    1.13
    ḿ
    1.13
    жав
    1.12
    rido
    1.11
     enseignants
    1.09
    epresidente
    1.09
    Activations Density 0.000%

    No Known Activations