© 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. 21766
    Prev
    Next
    INDEX
    Explanations

    tight clothes

    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
    大型
    0.46
     gowns
    0.40
    宽
    0.40
    eca
    0.40
     gown
    0.40
     넓
    0.40
    広い
    0.38
     ampio
    0.37
     large
    0.37
     gigante
    0.37
    POSITIVE LOGITS
    Tight
    0.72
     Tight
    0.71
     tight
    0.70
     skinny
    0.68
    tight
    0.66
    紧
    0.66
    緊
    0.63
     tighter
    0.61
     slim
    0.59
    Slim
    0.55
    Activations Density 0.005%

    No Known Activations