© 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. 70559
    Prev
    Next
    INDEX
    Explanations

    technical terms and components

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

    The neuron is keyed to pick out the main technical or content–bearing words (especially nouns) that serve as headings or topical keywords.

    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
     a
    -1.42
     vermutlich
    -1.08
     those
    -1.02
     damaligen
    -1.00
    țiunea
    -1.00
     these
    -0.99
     find
    -0.95
    u
    -0.95
     調整
    -0.95
     zweiten
    -0.93
    POSITIVE LOGITS
     camiset
    1.38
    ÜR
    1.26
    اقرأ
    1.20
     parut
    1.16
    Elekt
    1.14
    และ
    1.14
    は
    1.11
    lève
    1.11
    自体
    1.10
    слам
    1.10
    Activations Density 0.244%

    No Known Activations