© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34516
    Prev
    Next
    INDEX
    Explanations

    Add or update actions

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

    The neuron fires on programming identifiers—names of functions, classes, methods, properties, and other code symbols.

    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
    cocina
    -0.94
     Yesus
    -0.92
    nodo
    -0.91
    Breite
    -0.89
    Regula
    -0.88
    Consultant
    -0.85
    depart
    -0.85
    textt
    -0.85
    Tarif
    -0.84
    찐
    -0.83
    POSITIVE LOGITS
     Leigh
    0.85
    chloric
    0.83
     dabei
    0.82
    緹
    0.82
     ....
    0.81
    су
    0.80
    集群
    0.78
     Proceedings
    0.78
    诺
    0.77
    L
    0.75
    Activations Density 0.063%

    No Known Activations