© 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. 34-GEMMASCOPE-RES-131K
    7. 64465
    Prev
    Next
    INDEX
    Explanations

    questions, definitions, and prefixes

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

    The neuron flags alphanumeric vehicle model/designation tokens (e.g. brand names plus model numbers like “Changan CS35 Plus”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    demir
    -0.78
     agro
    -0.77
    AddressBook
    -0.76
    jstor
    -0.74
     amigo
    -0.74
     bebé
    -0.73
     querido
    -0.72
    teins
    -0.71
    Gros
    -0.71
     alegre
    -0.71
    POSITIVE LOGITS
     NEV
    0.98
     Batter
    0.90
    NIO
    0.88
     sales
    0.81
    onatos
    0.79
     understands
    0.78
    宜
    0.78
    Guide
    0.77
     BA
    0.75
     Lv
    0.75
    Activations Density 0.008%

    No Known Activations