© 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. 31-GEMMASCOPE-2-RES-65K
    7. 30618
    Prev
    Next
    INDEX
    Explanations

    relative narcissist

    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
    幼儿
    0.46
     дет
    0.42
    嫔
    0.41
    ഭ്യാസ
    0.41
    ('.')
    0.40
     بچوں
    0.40
    乌
    0.39
    栀
    0.39
    valmentaja
    0.39
    Children
    0.38
    POSITIVE LOGITS
     inherit
    0.53
     inheritance
    0.52
     filial
    0.50
     inherited
    0.49
     inheriting
    0.46
     inherits
    0.45
     executor
    0.42
     Inher
    0.42
     dementia
    0.41
     estates
    0.41
    Activations Density 0.037%

    No Known Activations