© 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. 157015
    Prev
    Next
    INDEX
    Explanations

    financial goals or investments

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

    AARP Member Discount

    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
     лечения
    0.49
     dinámica
    0.49
     evaluated
    0.46
     nonchal
    0.46
     требует
    0.45
     д
    0.45
     театра
    0.45
     кул
    0.45
    ઉસ
    0.44
     unpredict
    0.44
    POSITIVE LOGITS
    ون
    0.55
    ות
    0.54
    extr
    0.53
    aff
    0.52
    버
    0.50
    क्ष
    0.50
    ovll
    0.50
    όμε
    0.49
    aków
    0.49
    azion
    0.48
    Activations Density 0.000%

    No Known Activations