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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-65K
    7. 1840
    Prev
    Next
    INDEX
    Explanations

    emotions and feelings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_65k_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
     Parigi
    1.34
    ǎi
    1.30
     París
    1.29
    捞
    1.27
    撈
    1.26
    規模
    1.23
    ക്കിയി
    1.22
    多家
    1.18
     sacrificio
    1.16
    둰
    1.16
    POSITIVE LOGITS
     emotions
    1.74
     moods
    1.62
    情绪
    1.54
     emotion
    1.54
     feelings
    1.49
     anger
    1.47
     outbursts
    1.45
     mood
    1.42
     psych
    1.39
    emotion
    1.38
    Activations Density 1.091%

    No Known Activations