© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 40917
    Prev
    Next
    INDEX
    Explanations

    emotion recognition from facial expressions

    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_65k_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
    okhlov
    0.48
    比如說
    0.48
    omata
    0.46
    ovalo
    0.46
    atzeko
    0.46
    emper
    0.45
    onske
    0.45
    >(</
    0.44
    ību
    0.43
    ooi
    0.42
    POSITIVE LOGITS
     placenta
    0.43
     UIText
    0.40
     pomegranate
    0.39
     sanctions
    0.38
     เหมาะ
    0.38
    充
    0.38
    最大的
    0.37
     hashtag
    0.36
     brushing
    0.36
    efficacy
    0.36
    Activations Density 0.001%

    No Known Activations