© 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. 54707
    Prev
    Next
    INDEX
    Explanations

    person or personality

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

    personality traits and disorders

    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
     கண்க
    0.48
     Councilor
    0.48
     való
    0.47
    在该
    0.45
    a
    0.44
    ُوا
    0.44
     DispatchQueue
    0.44
     ሀ
    0.44
    aar
    0.44
     கலோரிகள்
    0.44
    POSITIVE LOGITS
     person
    0.90
    Persona
    0.88
     Persona
    0.86
     персо
    0.84
     Personality
    0.83
     PERSON
    0.82
    人格
    0.82
     personality
    0.81
    Personality
    0.81
     osoba
    0.81
    Activations Density 0.032%

    No Known Activations