© 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. 79044
    Prev
    Next
    INDEX
    Explanations

    show or duration related words

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

    This neuron activates on occurrences of lock‐related API calls (e.g. readLock(), writeLock()) and similar technical tokens.

    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
     for
    -0.92
     CGSize
    -0.88
    ActivityResult
    -0.82
    ！(
    -0.81
    putBoolean
    -0.80
     conoció
    -0.79
    컴
    -0.79
    ՝
    -0.79
    ласти
    -0.78
    зите
    -0.77
    POSITIVE LOGITS
    Afficher
    0.96
    show
    0.95
     piscinas
    0.94
     duración
    0.93
     showed
    0.93
     vlak
    0.93
     mostrando
    0.91
    artiges
    0.91
     show
    0.89
     LENGTH
    0.88
    Activations Density 0.000%

    No Known Activations