© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 8184
    Prev
    Next
    INDEX
    Explanations

    family story

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

    The neuron fires on formatted wedding‐announcement headings—i.e. titles containing “Wedding:” (or “wedding”) plus the names of the couple.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     constater
    -1.66
     desmotiv
    -1.45
     insegu
    -1.41
     maniere
    -1.39
    appears
    -1.39
     travailler
    -1.38
    錒
    -1.36
     lavorare
    -1.34
    himself
    -1.33
    konos
    -1.33
    POSITIVE LOGITS
     took
    1.63
     gave
    1.55
     did
    1.54
     was
    1.46
     we
    1.45
     our
    1.41
     went
    1.30
     had
    1.30
     my
    1.28
     came
    1.27
    Activations Density 0.025%

    No Known Activations