© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 2986
    Prev
    Next
    INDEX
    Explanations

    enthusiasm and excitement

    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
     =-\
    0.49
    咎
    0.46
    𝜌
    0.46
    )=-\
    0.44
     borderWidth
    0.44
    ដ
    0.44
    𠃍
    0.43
     deformable
    0.43
    糹
    0.43
    RENGTH
    0.43
    POSITIVE LOGITS
     excitement
    2.72
     excited
    2.44
     excitedly
    2.17
     enthusiasm
    2.09
     entusiasmo
    2.09
     excite
    2.06
    excited
    2.05
     Excited
    2.05
    兴奋
    1.98
     excites
    1.91
    Activations Density 0.003%

    No Known Activations