© 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. 34557
    Prev
    Next
    INDEX
    Explanations

    noun followed by category

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

    The neuron is triggered by specialized technical or scientific terms (e.g. complex medical, biological, or engineering jargon).

    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
     to
    -1.28
     Rektor
    -1.02
    vités
    -0.97
    éticos
    -0.96
     厂家
    -0.95
    SafeArea
    -0.94
     articol
    -0.91
    jaardag
    -0.91
     ため
    -0.91
     /#
    -0.90
    POSITIVE LOGITS
     colorear
    1.17
    ਆਂ
    1.12
     macetas
    1.05
    いかがでしたか
    1.02
    !
    1.02
     sonre
    0.99
    zondere
    0.97
     começa
    0.93
     strøm
    0.93
     llorar
    0.92
    Activations Density 0.147%

    No Known Activations