© 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. 22-GEMMASCOPE-RES-131K
    7. 26496
    Prev
    Next
    INDEX
    Explanations

    romantic relationships and honeymoons

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

    The neuron strongly activates on terms advertising romantic getaways—words like “romantic,” “honeymoon,” “getaway,” “date night,” or “couples,” signaling a honeymoon or couple-oriented vacation context.

    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
    toplasm
    -1.09
     Dimensions
    -0.99
     community
    -0.96
    NECTIONS
    -0.91
    牝
    -0.90
    olith
    -0.88
    øl
    -0.88
     FIFTH
    -0.87
     dzisiaj
    -0.87
     verschillende
    -0.86
    POSITIVE LOGITS
     couples
    1.62
    两人
    1.51
     romantic
    1.47
     couple
    1.45
     вд
    1.23
     their
    1.20
    二人
    1.16
     berdua
    1.15
     Couples
    1.15
     yourselves
    1.14
    Activations Density 0.029%

    No Known Activations