© 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. 68949
    Prev
    Next
    INDEX
    Explanations

    use, used, for, to

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

    The neuron detects descriptive performance or resource‐usage claims (e.g. “occupies a low footprint,” “deploys fast,” etc.).

    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
     tailles
    -1.32
    也非常
    -1.17
     bollywood
    -1.16
     Secre
    -1.16
     impra
    -1.14
     airpods
    -1.14
    ">“
    -1.13
    uttgart
    -1.13
    ฬ
    -1.11
     closeup
    -1.09
    POSITIVE LOGITS
     your
    1.37
     only
    1.25
     process
    1.23
     JavaScript
    1.16
     for
    1.13
     used
    1.13
     operations
    1.12
     processes
    1.11
     to
    1.10
     software
    1.09
    Activations Density 0.022%

    No Known Activations