© 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. 41-GEMMASCOPE-2-RES-262K
    7. 31598
    Prev
    Next
    INDEX
    Explanations

    epitome, quintessential, embodiment

    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_all/layer_41_width_262k_l0_big
    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
     surprisingly
    0.52
     surprising
    0.42
    surprisingly
    0.41
     curiously
    0.39
    Surprisingly
    0.39
     isomorphisms
    0.38
    ঘাত
    0.37
    _{*}$
    0.37
     Surprisingly
    0.36
    更换
    0.36
    POSITIVE LOGITS
     epitome
    1.39
     quintessential
    1.27
     вопло
    1.25
     embodiment
    1.19
     embodies
    1.01
     ultimate
    0.97
     prototypical
    0.96
     embod
    0.96
     embody
    0.96
     embodying
    0.95
    Activations Density 0.002%

    No Known Activations