© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 31986
    Prev
    Next
    INDEX
    Explanations

    passionate feeling or interest

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

    the presence of words signaling personal emotions or enthusiasm (e.g. feel, passion, 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
    ladas
    -0.89
    婀
    -0.82
    ilton
    -0.81
     PURCHASE
    -0.81
    nio
    -0.80
     Prix
    -0.80
     Aguilar
    -0.79
    liter
    -0.79
    уме
    -0.79
     kır
    -0.78
    POSITIVE LOGITS
     passion
    4.94
    passion
    4.13
     passionate
    4.09
    Passion
    3.98
     Passion
    3.78
     passionately
    3.20
     pasión
    3.16
     passions
    3.02
     passione
    2.97
     apasion
    2.73
    Activations Density 0.046%

    No Known Activations