© 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. 34-GEMMASCOPE-RES-131K
    7. 59006
    Prev
    Next
    INDEX
    Explanations

    names and specific concepts

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

    The neuron responds to technical scientific terminology and formulaic expressions (e.g. chemical symbols, physical effects, variables, and equation syntax).

    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
    FORCE
    -0.81
    wild
    -0.77
     دوست
    -0.76
     Support
    -0.75
     イ
    -0.74
    support
    -0.73
     ゴ
    -0.72
     constitutive
    -0.71
    pois
    -0.71
    AnimationsModule
    -0.71
    POSITIVE LOGITS
     Kondo
    0.94
     impurity
    0.78
    código
    0.73
    탁
    0.70
     hybridization
    0.67
    Wider
    0.67
    cipa
    0.67
    ạp
    0.67
    Método
    0.67
     হয়
    0.66
    Activations Density 0.038%

    No Known Activations