© 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. 66345
    Prev
    Next
    INDEX
    Explanations

    URLs and dates

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

    The neuron strongly activates on the forward-slash characters used in URL paths and separators.

    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
     in
    -1.06
    ЛЕ
    -1.05
    gradable
    -0.99
     Juin
    -0.95
    dA
    -0.94
    нена
    -0.93
     século
    -0.91
     Galerie
    -0.91
    цар
    -0.91
    ШЕ
    -0.90
    POSITIVE LOGITS
    consejos
    1.01
    empleado
    0.99
    seleccion
    0.98
    Encontra
    0.96
    のご紹介
    0.96
    comentario
    0.96
    encontra
    0.95
    Bonuses
    0.95
     hổ
    0.94
    insertar
    0.93
    Activations Density 0.003%

    No Known Activations