© 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. 34-GEMMASCOPE-RES-131K
    7. 117790
    Prev
    Next
    INDEX
    Explanations

    java code blocks

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

    The neuron fires on literal constant values (e.g. numeric or string literals) in 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_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
     
    -1.73
     Особенно
    -1.04
    newnode
    -0.95
    ilta
    -0.85
     within
    -0.85
     Within
    -0.84
     localizar
    -0.81
    . 
    -0.81
     сок
    -0.81
     eventuali
    -0.80
    POSITIVE LOGITS
    System
    1.23
     java
    1.13
    <>();
    1.07
     boolean
    1.02
     System
    1.00
     می‌باشد
    0.93
     String
    0.93
     ArrayList
    0.92
    noinspection
    0.92
     Optional
    0.86
    Activations Density 0.001%

    No Known Activations