© 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. 580
    Prev
    Next
    INDEX
    Explanations

    entity website references

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

    The neuron activates on uppercase or title-cased proper nouns and acronyms (e.g. conference names, brand/product names, organization abbreviations).

    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
    madonna
    -1.19
     både
    -1.12
    chile
    -1.10
    citroen
    -1.08
     mété
    -1.07
    CLUDE
    -1.05
     sejak
    -1.00
     şeklinde
    -1.00
    БО
    -0.99
     การ
    -0.98
    POSITIVE LOGITS
     website
    2.16
     if
    1.59
     websites
    1.46
    website
    1.42
     webpage
    1.40
     homepage
    1.32
     page
    1.26
    www
    1.19
     after
    1.16
     www
    1.13
    Activations Density 0.044%

    No Known Activations