© 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. 8867
    Prev
    Next
    INDEX
    Explanations

    love words and emojis

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

    love and emotional connection

    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
    補助
    0.50
    吆
    0.50
     deterrence
    0.49
    嬸
    0.48
    陝
    0.48
    斡
    0.48
     پیسہ
    0.46
     deterrent
    0.46
     издания
    0.46
     ogranic
    0.46
    POSITIVE LOGITS
     عشق
    0.97
    爱情
    0.93
     love
    0.92
     사랑
    0.92
     romant
    0.89
    💏
    0.87
     Love
    0.86
     ప్రేమ
    0.86
    💑
    0.86
     প্রেমের
    0.84
    Activations Density 0.240%

    No Known Activations