© 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. 93179
    Prev
    Next
    INDEX
    Explanations

    references and names

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

    The neuron activates on multi-word capitalized names or titles—that is, proper nouns such as character names or song/album titles.

    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
     of
    -2.95
     this
    -2.00
     the
    -1.98
    !
    -1.80
     information
    -1.80
     our
    -1.75
     so
    -1.74
     all
    -1.67
     now
    -1.66
     in
    -1.64
    POSITIVE LOGITS
    Ingredi
    1.77
     refroid
    1.77
    greja
    1.65
    퐼
    1.63
     échange
    1.60
    Recept
    1.60
    Gön
    1.59
     coû
    1.59
    Krok
    1.59
    Buna
    1.58
    Activations Density 0.000%

    No Known Activations