© 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. 22894
    Prev
    Next
    INDEX
    Explanations

    heavy/heavier/heavyweight concept

    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
    CFLAGS
    0.37
    addAlignment
    0.36
     mind
    0.34
    awards
    0.34
     imprime
    0.34
     lb
    0.34
    儂
    0.33
     enfants
    0.33
    চ্য
    0.33
    ฒ
    0.33
    POSITIVE LOGITS
     Heavy
    1.05
     heavy
    1.02
    Heavy
    1.00
     heavier
    0.98
    heavy
    0.98
     cięż
    0.89
     ağır
    0.86
    重
    0.84
     тяже
    0.83
     भारी
    0.78
    Activations Density 0.000%

    No Known Activations