© 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. 13788
    Prev
    Next
    INDEX
    Explanations

    quantum mechanics and related concepts

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

    The neuron strongly activates on in‐line mathematical notation—especially LaTeX‐style formulas and Dirac bra-ket constructs.

    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
     السياس
    -1.25
     use
    -1.21
     –
    -1.20
     zrobić
    -1.18
     getAddress
    -1.13
    se
    -1.13
     is
    -1.11
     said
    -1.08
    祝い
    -1.06
     getIs
    -1.06
    POSITIVE LOGITS
     coloridos
    1.40
     retratos
    1.33
    　↓
    1.30
    闈
    1.27
    AMENTO
    1.27
    Ку
    1.27
    灕
    1.25
    omości
    1.24
     muñeco
    1.23
     CascadeType
    1.23
    Activations Density 0.022%

    No Known Activations