© 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. 68732
    Prev
    Next
    INDEX
    Explanations

    interactions and networks

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

    The neuron strongly activates on technical terms and morphemes related to embodied/enactive cognition and sensorimotor organism–environment interactions.

    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
     will
    -1.34
     आपके
    -1.18
    َ
    -1.12
     шокола
    -1.12
     promise
    -1.12
    чай
    -1.09
    鴣
    -1.07
     nguyen
    -1.02
    atorio
    -1.01
    projekt
    -1.01
    POSITIVE LOGITS
     plutôt
    1.55
     وليس
    1.41
    ֝
    1.30
     洗面
    1.27
     coloridas
    1.23
     requisito
    1.23
     угло
    1.21
     estudiar
    1.20
     interesados
    1.17
    =>'
    1.15
    Activations Density 0.053%

    No Known Activations