© 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. 33936
    Prev
    Next
    INDEX
    Explanations

    configuration attributes

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

    This neuron activates on configuration or attribute names (i.e. parameter/option keys) in code or markup.

    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
    плуата
    -1.15
    liothè
    -1.09
    Notae
    -1.01
     başlad
    -1.00
    珍しい
    -0.97
     vérification
    -0.96
    了出去
    -0.96
    Afrika
    -0.95
     birlikte
    -0.94
     reçoit
    -0.93
    POSITIVE LOGITS
    —
    0.97
     that
    0.97
    那样
    0.91
     hề
    0.91
    */}
    0.91
    "';
    0.90
     culturali
    0.89
    i
    0.88
     regarding
    0.88
     his
    0.86
    Activations Density 0.010%

    No Known Activations