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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-262K
    7. 8401
    Prev
    Next
    INDEX
    Explanations

    fundamental physics concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_9_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
     عليك
    1.06
     Passport
    0.98
     삭제
    0.92
     욕
    0.91
    grocery
    0.89
     Teens
    0.89
     좋은
    0.89
    meals
    0.88
    𝐛
    0.88
    𝐰
    0.88
    POSITIVE LOGITS
     physicists
    1.27
     astrophysics
    1.09
     ushered
    1.02
     fermions
    1.00
     physicist
    0.99
     chiral
    0.99
     QCD
    0.98
     cosmology
    0.97
     preferentially
    0.93
     জিয়া
    0.93
    Activations Density 0.281%

    No Known Activations