© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 28374
    Prev
    Next
    INDEX
    Explanations

    strong desire or craving

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

    strong desire and wanting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ме
    0.55
    ad
    0.53
    分手
    0.53
    털
    0.53
    ой
    0.53
    инг
    0.52
    班
    0.52
    巧妙
    0.51
    怔
    0.50
    τ
    0.49
    POSITIVE LOGITS
     desire
    1.63
     craving
    1.54
     cravings
    1.41
     yearning
    1.38
     desiderio
    1.33
     longing
    1.30
     desires
    1.27
     want
    1.27
     yearn
    1.26
     désir
    1.21
    Activations Density 0.082%

    No Known Activations