© 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. 39916
    Prev
    Next
    INDEX
    Explanations

    somebody or something

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

    The neuron is strongly activated by domain‐specific content words (technical or scientific jargon) in otherwise formal, informational text.

    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
    と言われる
    -1.10
    就可以了
    -1.02
     today
    -1.02
    即可
    -0.96
     now
    -0.92
    द्धि
    -0.91
     alltid
    -0.89
     случае
    -0.89
     всегда
    -0.88
    werkt
    -0.87
    POSITIVE LOGITS
     someone
    1.72
     somebody
    1.59
     something
    1.50
    someone
    1.44
     Someone
    1.34
    somebody
    1.34
    Someone
    1.25
     quelqu
    1.23
     alguém
    1.23
     offenbar
    1.16
    Activations Density 0.054%

    No Known Activations