© 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. 76720
    Prev
    Next
    INDEX
    Explanations

    optical microcavity, magnonic crystals, negative

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

    The neuron fires strongly on specialized multi‐word technical jargon and compound noun phrases (e.g. “band‐structure engineering,” “low‐loss propagation,” “non‐Hermitian optical microcavity”), i.e. domain‐specific scientific terminology.

    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
     subscribers
    -0.84
     sfer
    -0.78
     subscriptions
    -0.72
     francês
    -0.72
     Subscribers
    -0.71
    바
    -0.69
     جشن
    -0.69
     Awak
    -0.68
     actos
    -0.68
    Cake
    -0.68
    POSITIVE LOGITS
     Penrose
    1.10
     lattices
    0.94
     esfuerzan
    0.88
     нега
    0.86
    Negative
    0.83
     negative
    0.83
     negativity
    0.83
     réaliser
    0.82
    Rechts
    0.82
     Negative
    0.81
    Activations Density 0.030%

    No Known Activations