© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 108080
    Prev
    Next
    INDEX
    Explanations

    emotional connections and attraction

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    🫢
    0.52
    ánea
    0.48
     cambiamenti
    0.46
     Größen
    0.46
     மஞ்சள்
    0.44
     résultats
    0.43
     غلط
    0.43
     cambiamento
    0.43
     الجذر
    0.42
     Résultats
    0.41
    POSITIVE LOGITS
    将
    0.45
    爱
    0.42
    愛
    0.41
    nergy
    0.39
     hating
    0.39
     חו
    0.38
    acy
    0.38
     musik
    0.38
    emaking
    0.38
    音乐
    0.37
    Activations Density 0.028%

    No Known Activations