© 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. 28450
    Prev
    Next
    INDEX
    Explanations

    health and hygiene

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

    health and classification

    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
    Istanbul
    0.46
     শাসকদের
    0.43
    innerHeight
    0.43
     修
    0.42
    Xiao
    0.41
    Undo
    0.41
    maxn
    0.40
    修
    0.40
     သိ
    0.40
    Arqu
    0.40
    POSITIVE LOGITS
     epidemi
    0.63
     chiropractor
    0.52
     septic
    0.52
     Veterin
    0.51
    тной
    0.51
     diagnost
    0.50
     hygien
    0.50
     și
    0.50
     orthopedic
    0.49
     restrooms
    0.49
    Activations Density 0.000%

    No Known Activations