© 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. 36367
    Prev
    Next
    INDEX
    Explanations

    Q:

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

    The neuron activates on the token “signed,” i.e. it detects occurrences of the word “signed.”

    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
     all
    -1.55
     OBITUARY
    -1.22
     five
    -1.12
    слен
    -1.12
    hubanes
    -1.05
     six
    -1.03
     understand
    -1.02
    jego
    -1.02
     then
    -1.02
    all
    -1.02
    POSITIVE LOGITS
    onaut
    1.16
    messung
    1.15
    Diret
    1.12
     мужская
    1.08
    NCIS
    1.05
    bindet
    1.05
    嗱
    1.05
    并非
    1.04
    を探す
    1.03
     angesehen
    1.02
    Activations Density 0.000%

    No Known Activations