© 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. 3349
    Prev
    Next
    INDEX
    Explanations

    Q: or Background

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

    The neuron detects fully qualified Java package and class names in package or import declarations.

    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
    ̠
    -0.85
    FirebaseDatabase
    -0.81
     Мо
    -0.79
    сный
    -0.79
     попа
    -0.78
     lemari
    -0.78
    dff
    -0.75
    未満
    -0.75
     Па
    -0.75
    Approx
    -0.74
    POSITIVE LOGITS
     Kannada
    0.90
    AppMethodBeat
    0.90
     LinkedList
    0.85
    LinkedList
    0.85
    Lorenzo
    0.84
     psychiat
    0.84
    ។
    0.84
    ジャマ
    0.83
    ragalactic
    0.82
     Coimbatore
    0.82
    Activations Density 0.004%

    No Known Activations