© 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. 15130
    Prev
    Next
    INDEX
    Explanations

    time remaining or elapsed

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

    The neuron is triggered by numeric tokens and expressions—especially game scores, times, and statistical figures.

    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
     póster
    -1.27
     ekolog
    -1.18
     producent
    -1.03
     constater
    -1.02
     vieilles
    -1.02
     charmant
    -1.02
    íp
    -1.00
     verhind
    -1.00
     fotografie
    -1.00
     citoyens
    -0.98
    POSITIVE LOGITS
     entfernt
    1.02
    堺
    0.99
    大致
    0.95
     ago
    0.91
    \
    0.90
    выя
    0.87
    M
    0.87
    只剩下
    0.87
     even
    0.85
    思路
    0.85
    Activations Density 0.006%

    No Known Activations