© 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. 227374
    Prev
    Next
    INDEX
    Explanations

    steroids, drugs, and muscle growth

    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
    3
    0.51
    os
    0.50
    塞
    0.48
     namen
    0.47
    2
    0.46
    ２
    0.46
    ajana
    0.44
    ｉ
    0.43
    iv
    0.43
    物的
    0.43
    POSITIVE LOGITS
    polynomial
    0.50
     restructuring
    0.47
     ಅದ
    0.46
     Highlands
    0.45
     Burkina
    0.45
    ೀರಿ
    0.45
     ಬಹು
    0.44
    ுமி
    0.44
    ర్రీ
    0.44
     তৃণ
    0.44
    Activations Density 0.000%

    No Known Activations