© 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. 71663
    Prev
    Next
    INDEX
    Explanations

    compound nouns and phrases

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

    The neuron detects multiword, capitalized segments of organization or institutional names.

    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
     mobilen
    -1.78
     originalen
    -1.46
     augusti
    -1.46
     a
    -1.44
     Komun
    -1.42
     maksimal
    -1.36
     papir
    -1.35
     vokal
    -1.34
     plakat
    -1.33
     restoran
    -1.31
    POSITIVE LOGITS
    も行
    1.41
    もので
    1.40
    IActionResult
    1.31
    orghe
    1.30
    ginous
    1.29
    さんへ
    1.28
    を開催
    1.28
    ようになる
    1.28
     ocurrió
    1.25
     rozwój
    1.25
    Activations Density 0.139%

    No Known Activations