© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 165451
    Prev
    Next
    INDEX
    Explanations

    exercise and strengthening

    np_acts-logits-general · gemini-2.5-flash-lite

    strengthen or improve health

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     அணுக
    0.43
    城区
    0.40
     உலகில்
    0.39
    ̡
    0.39
    tywn
    0.38
     ማለት
    0.38
     বিদ্রোহ
    0.38
     божомолдор
    0.38
    ℍ
    0.38
     eenvoud
    0.38
    POSITIVE LOGITS
    锻炼
    0.56
    鍛
    0.55
     refresh
    0.49
    培养
    0.49
     stär
    0.49
     honing
    0.49
     buildup
    0.48
     testa
    0.47
    經驗
    0.46
     deple
    0.46
    Activations Density 0.290%

    No Known Activations