© 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. 27425
    Prev
    Next
    INDEX
    Explanations

    legal and technical phrases

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

    The neuron activates on numeric tokens, picking out numbers (including digits, percentages, and numeric constants) wherever they appear.

    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
     accesorios
    -1.27
     efekty
    -0.97
     geliyor
    -0.97
    dhury
    -0.94
     използ
    -0.94
     disfraces
    -0.94
     ofrecerte
    -0.94
     soluções
    -0.93
     miest
    -0.93
     всичко
    -0.93
    POSITIVE LOGITS
    乏
    0.92
     trebu
    0.90
     semula
    0.90
     недорого
    0.88
    itzt
    0.88
    iibo
    0.87
     spart
    0.84
     regained
    0.83
    月刊
    0.82
    をご覧
    0.82
    Activations Density 0.007%

    No Known Activations