© 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. 34-GEMMASCOPE-RES-131K
    7. 82315
    Prev
    Next
    INDEX
    Explanations

    expressing love

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

    The neuron primarily detects occurrences of the word “love” (especially capitalized or emphatic “LOVE”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    那边
    -1.15
     OBSERVATIONS
    -1.13
     a
    -1.13
     unangemessene
    -1.09
     desired
    -1.08
    矇
    -1.05
    celotti
    -1.02
    meneu
    -1.02
    |_{
    -1.02
    記入
    -1.00
    POSITIVE LOGITS
     how
    2.75
     that
    1.98
     the
    1.70
     seeing
    1.45
     to
    1.43
    How
    1.24
     hearing
    1.23
     watching
    1.19
     having
    1.14
    having
    1.13
    Activations Density 0.016%

    No Known Activations