© 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. 22-GEMMASCOPE-RES-131K
    7. 40009
    Prev
    Next
    INDEX
    Explanations

    code or data structures

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

    The neuron is looking for numeric tokens (numbers or digit sequences).

    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
     they
    -0.77
     staff
    -0.76
     أحمد
    -0.74
    vets
    -0.73
     able
    -0.73
     вред
    -0.72
     dort
    -0.71
     уход
    -0.71
     closing
    -0.70
     active
    -0.70
    POSITIVE LOGITS
     again
    1.27
    こちらも
    0.98
    again
    0.90
     Again
    0.90
    Again
    0.87
    これも
    0.87
    不動産
    0.84
    بح
    0.82
    æl
    0.82
     dissimilar
    0.81
    Activations Density 0.039%

    No Known Activations