© 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. 9461
    Prev
    Next
    INDEX
    Explanations

    cures for illnesses

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

    cures and health remedies

    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
    蹼
    0.54
     세율
    0.54
     정책
    0.53
     במהלך
    0.52
    TransactionLog
    0.52
     მნიშვნელ
    0.51
    באנגלית
    0.51
    頨
    0.51
    交易
    0.50
    空港
    0.50
    POSITIVE LOGITS
     cures
    0.61
     cured
    0.59
     cure
    0.59
     antiseptic
    0.57
     curing
    0.56
     bronchitis
    0.55
     medicines
    0.54
     herbal
    0.54
     rheumatism
    0.54
     cough
    0.52
    Activations Density 0.003%

    No Known Activations