© 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. 121923
    Prev
    Next
    INDEX
    Explanations

    stock market and financial reports

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

    how to drink

    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
    蕖
    0.50
    accuracy
    0.47
    淦
    0.45
    Bass
    0.45
    Κα
    0.44
    专业的
    0.42
    颗粒
    0.42
    疖
    0.42
    icies
    0.42
     комплек
    0.42
    POSITIVE LOGITS
     remuneration
    0.46
     diffé
    0.41
     orator
    0.40
     Jawaharlal
    0.40
     amulet
    0.40
     هنر
    0.40
     TVs
    0.39
     symbolizes
    0.39
     révolution
    0.39
     televisions
    0.39
    Activations Density 0.001%

    No Known Activations