© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 9353
    Prev
    Next
    INDEX
    Explanations

    recursive file inclusion

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

    The neuron fires on numeric tokens—digits or numbers (including version numbers and numeric literals).

    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
     registró
    -1.01
    䰀
    -0.92
     creó
    -0.92
     nació
    -0.90
     identical
    -0.87
     individualized
    -0.84
    ⮚
    -0.84
     einzeln
    -0.84
     advirtió
    -0.84
     cuentan
    -0.84
    POSITIVE LOGITS
     Autó
    1.17
     ſer
    0.98
    
    0.97
    ブログ
    0.94
    meyen
    0.94
    Το
    0.91
     Mishra
    0.90
    bungen
    0.90
     mía
    0.89
    <0xEF>
    0.88
    Activations Density 0.026%

    No Known Activations