© 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. 22-GEMMASCOPE-RES-131K
    7. 33189
    Prev
    Next
    INDEX
    Explanations

    package/import statements

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

    This neuron detects tokens that are part of fully qualified Java/Android import package paths (e.g. “android.view.”, “androidx.recyclerview.widget.”).

    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
     kuiten
    -1.19
    蟶
    -1.07
    -1.06
    août
    -1.05
     imponer
    -1.04
    瞠
    -1.02
    zkiem
    -1.01
    martre
    -1.00
    jaro
    -1.00
     assailed
    -0.99
    POSITIVE LOGITS
    ΠΑ
    1.05
     reco
    1.05
    which
    1.01
    atio
    1.00
    ς
    0.99
    ical
    0.99
    ire
    0.97
    ᴡ
    0.97
     voll
    0.95
    ところは
    0.94
    Activations Density 0.220%

    No Known Activations