© 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. 3087
    Prev
    Next
    INDEX
    Explanations

    smile, smiles, smiling, smiled

    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
    導
    0.49
    inertia
    0.49
    រប
    0.47
    懼
    0.47
    ็ง
    0.46
    ើង
    0.46
     conductivity
    0.44
    惰
    0.44
    ធាតុ
    0.44
     perpendicularly
    0.42
    POSITIVE LOGITS
     smile
    2.63
     smiled
    2.34
     smiles
    2.34
     Smile
    2.30
     улы
    2.22
    Smile
    2.20
     smiling
    2.16
    smile
    2.11
     sonrisa
    2.03
    Smiling
    1.96
    Activations Density 0.008%

    No Known Activations