© 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. 5862
    Prev
    Next
    INDEX
    Explanations

    buy medication online

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

    adult products and shopping

    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
     محور
    0.19
     Calyce
    0.19
    遍历
    0.18
     بعض
    0.18
    舴
    0.17
     شكله
    0.17
    糇
    0.17
     نہیں۔
    0.17
     মুখো
    0.17
     نتیجه
    0.17
    POSITIVE LOGITS
    como
    0.25
    conto
    0.22
    casino
    0.22
    harga
    0.22
    Como
    0.22
    Casino
    0.22
    а
    0.21
     Como
    0.21
    о
    0.21
    az
    0.21
    Activations Density 0.812%

    No Known Activations