© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 118972
    Prev
    Next
    INDEX
    Explanations

    physical phenomena and signals

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

    The main thing this neuron does is detect specialized technical or scientific jargon—particularly domain-specific noun phrases referring to signals, emissions, devices, or physical phenomena.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     considerando
    -1.34
     ..........
    -1.23
    ……
    -1.22
     ........
    -1.20
     débris
    -1.16
    ……..
    -1.15
    屌
    -1.15
    Jaunes
    -1.14
     boîtes
    -1.14
     ……
    -1.14
    POSITIVE LOGITS
     from
    1.30
    СЯ
    1.16
    纾
    1.14
    İN
    1.12
     to
    1.11
     براي
    1.09
    bular
    1.08
     is
    1.08
    СКА
    1.08
     braccia
    1.07
    Activations Density 0.666%

    No Known Activations