© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 3544
    Prev
    Next
    INDEX
    Explanations

    mutable or writable data

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

    This neuron strongly activates on Android/Java API identifiers (e.g. SQLiteDatabase, getReadableDatabase, Bitmap.createBitmap, mutable Bitmap, etc.).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     samego
    -0.72
     dầu
    -0.72
     Roof
    -0.71
    ToDisplay
    -0.71
    printList
    -0.71
    deploy
    -0.71
    Conten
    -0.69
     räum
    -0.69
    Macro
    -0.68
    Blocked
    -0.68
    POSITIVE LOGITS
     mutable
    2.55
     writable
    2.36
    Mutable
    2.28
    mutable
    2.16
    writable
    2.05
     Mutable
    1.94
     editable
    1.94
     modif
    1.88
    modifiable
    1.62
    Writable
    1.60
    Activations Density 0.047%

    No Known Activations