© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 7140
    Prev
    Next
    INDEX
    Explanations

    java methods

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

    The neuron activates on the “.” character in code, i.e. it detects dots used for member access (method/field calls) and decimal points.

    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
    printf
    -0.93
    という
    -0.89
     brome
    -0.85
     assister
    -0.82
     Csv
    -0.81
    riages
    -0.78
    ndata
    -0.77
     excur
    -0.77
    CITATION
    -0.74
     ANS
    -0.73
    POSITIVE LOGITS
     jugando
    0.83
     БО
    0.82
     celos
    0.81
     HashMap
    0.79
     loving
    0.78
     Ně
    0.78
     Size
    0.77
     lógico
    0.77
    scre
    0.77
     lukewarm
    0.77
    Activations Density 0.002%

    No Known Activations