© 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. 6801
    Prev
    Next
    INDEX
    Explanations

    funeral home

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

    funeral homes and burial grounds

    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
    上涨
    0.39
    日报
    0.39
     Oxidation
    0.38
     व्हाउचर
    0.38
     Metabolism
    0.37
    蠹
    0.37
    aporation
    0.37
    প্রত্য
    0.36
    कोलॉजी
    0.36
     العديد
    0.35
    POSITIVE LOGITS
     paj
    0.37
     funerals
    0.36
     chapel
    0.35
     telephones
    0.35
     spl
    0.35
    殯
    0.34
    РА
    0.34
     ил
    0.34
     qr
    0.34
     CHAP
    0.34
    Activations Density 0.006%

    No Known Activations