© 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. 27188
    Prev
    Next
    INDEX
    Explanations

    human life, demand strict, taking loans

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

    possibilities and statements of fact

    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
     lin
    0.49
     Porsche
    0.49
     есть
    0.47
     Б
    0.46
    さんは
    0.46
     так
    0.45
     ওয়ার
    0.44
     Nvidia
    0.44
     Emotional
    0.44
     порт
    0.44
    POSITIVE LOGITS
     anglès
    0.47
    殮
    0.44
     शक्यता
    0.43
    ermost
    0.42
    hlas
    0.41
     власти
    0.40
    当局
    0.40
    家人
    0.40
    čenje
    0.40
     astonished
    0.40
    Activations Density 0.000%

    No Known Activations