© 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. 27020
    Prev
    Next
    INDEX
    Explanations

    technical specifications and code comments

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

    The neuron fires on uppercase programming or assembly keywords and identifiers (e.g. ALIGN, EXTERN, PUBLIC, PROC, etc.).

    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
     preços
    -0.93
    モチ
    -0.93
     loginUser
    -0.93
    Docente
    -0.91
    Medidas
    -0.90
    Organizador
    -0.90
     Rhapsody
    -0.90
     FREDERICK
    -0.89
    Soporte
    -0.89
     Tamanho
    -0.89
    POSITIVE LOGITS
     gick
    1.08
    ✭
    1.00
    tembro
    0.99
    siella
    0.97
    阑
    0.94
     vermelhas
    0.94
    Élet
    0.91
    กร
    0.91
     Съ
    0.91
    сибир
    0.91
    Activations Density 0.036%

    No Known Activations