© 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. 65617
    Prev
    Next
    INDEX
    Explanations

    Sunset Blvd.Network Penetration

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

    The neuron is looking for test‐related identifiers—e.g. JUnit/Test/it declarations 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_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
    скую
    -0.96
    chaussures
    -0.90
     fenti
    -0.88
     julie
    -0.88
     стала
    -0.88
    ají
    -0.86
    ﾛ
    -0.85
    aikan
    -0.84
     kasih
    -0.84
     daca
    -0.83
    POSITIVE LOGITS
     then
    1.56
     namentlich
    1.05
    __':
    1.01
     Then
    1.00
     utilizamos
    0.96
    鹮
    0.91
    Then
    0.91
    에서는
    0.89
     blame
    0.88
    logiques
    0.88
    Activations Density 0.002%

    No Known Activations