© 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. 54478
    Prev
    Next
    INDEX
    Explanations

    personality disorders

    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
     Prakash
    0.45
    <unused26>
    0.42
    蘊
    0.42
     Symbols
    0.41
     seguenti
    0.41
     Xml
    0.40
    Ticker
    0.39
     Isometric
    0.39
    鼾
    0.38
    pcion
    0.38
    POSITIVE LOGITS
     borderline
    0.76
    Border
    0.75
     Border
    0.71
    border
    0.62
     border
    0.60
     personality
    0.56
     बॉर्डर
    0.56
     NPD
    0.52
    BORDER
    0.51
     antisocial
    0.48
    Activations Density 0.031%

    No Known Activations