© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 84753
    Prev
    Next
    INDEX
    Explanations

    personality and social traits

    np_acts-logits-general · gemini-2.5-flash-lite

    shy, introvert, quiet

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    ymbol
    0.41
     ridiculous
    0.41
    ignore
    0.39
     الساعه
    0.39
    ਬ
    0.38
     knowledge
    0.38
     restoration
    0.38
     அறிவு
    0.38
    dangerous
    0.38
     आरमार
    0.38
    POSITIVE LOGITS
     shy
    1.12
     introvert
    0.88
     Shy
    0.83
     timid
    0.82
    腼
    0.81
    shy
    0.71
     extro
    0.68
     intro
    0.66
     outgoing
    0.64
     blushing
    0.63
    Activations Density 0.204%

    No Known Activations