© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 21407
    Prev
    Next
    INDEX
    Explanations

    vibrating with excitement and anticipation

    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_40_width_262k_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
    咎
    0.47
     देन
    0.46
    蔽
    0.45
    诬
    0.44
    批评
    0.43
     ด่า
    0.41
     ಕಂಡ
    0.40
    }=-\
    0.40
     কৰ
    0.40
    మర్శ
    0.40
    POSITIVE LOGITS
     excitement
    2.88
     excited
    2.52
     excitedly
    2.33
     excite
    2.19
    excited
    2.14
     Excited
    2.13
    兴奋
    2.05
     excites
    2.05
     excitation
    1.98
     exciting
    1.92
    Activations Density 0.015%

    No Known Activations