© 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. 16296
    Prev
    Next
    INDEX
    Explanations

    love, horoscope, and spiritual advice

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

    you/your/love/relationship

    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
     usamos
    0.53
    켰
    0.50
     табли
    0.50
    하였습니다
    0.48
    аз
    0.47
     कराना
    0.46
    рифмети
    0.46
    #/
    0.46
    쌌
    0.46
     உற்ப
    0.45
    POSITIVE LOGITS
     Capricorn
    0.59
     Horoscope
    0.57
     bientôt
    0.55
     turmoil
    0.55
     indulging
    0.54
     તમારે
    0.53
     ljubav
    0.51
     astral
    0.51
     आध्यात्मिक
    0.51
    恋
    0.51
    Activations Density 0.062%

    No Known Activations