© 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-IT
    5. 40-GEMMASCOPE-2-RES-65K
    7. 50741
    Prev
    Next
    INDEX
    Explanations

    soft skills, emotional intelligence

    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_40_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
     ㅛ
    0.42
    क्सी
    0.41
     기능
    0.40
    тельное
    0.40
    Absolute
    0.39
    арма
    0.38
     المستقيم
    0.38
    ➳
    0.37
    ციის
    0.37
     respekt
    0.37
    POSITIVE LOGITS
     soft
    2.03
     Soft
    1.87
    Soft
    1.80
    soft
    1.79
    软
    1.65
     सॉफ्ट
    1.64
     SOFT
    1.62
     softer
    1.52
    SOFT
    1.50
     мяг
    1.48
    Activations Density 0.060%

    No Known Activations