© 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. 22-GEMMASCOPE-RES-131K
    4. 95349
    Prev
    Next
    INDEX
    Explanations

    otherness or alternatives

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

    The neuron fires on words that denote part-whole or distribution relationships—terms like “shares,” “jurisdiction,” “distributed,” “similar,” “portion,” and their linking prepositions (of, in, to) indicating how something is allocated, compared, or spread.

    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
     uiteindelijk
    -1.13
     nové
    -1.11
    grazie
    -1.07
     tyto
    -1.05
     trebuie
    -1.05
     biztons
    -0.98
    სქოლიო
    -0.97
    Saluti
    -0.96
     either
    -0.96
    reté
    -0.96
    POSITIVE LOGITS
     others
    2.30
     other
    2.14
     lainnya
    1.80
    其他
    1.70
    อื่น
    1.66
    others
    1.55
     других
    1.48
     अन्य
    1.40
     elsewhere
    1.39
     سایر
    1.38
    Activations Density 0.064%

    No Known Activations