© 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. 58513
    Prev
    Next
    INDEX
    Explanations

    property followed by description

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

    property taxes and management

    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
    ك
    1.09
    ين
    0.81
    ۔
    0.80
    ه
    0.80
    。
    0.80
    は
    0.76
    اقه
    0.75
    ف
    0.74
    يل
    0.73
    ੁ
    0.73
    POSITIVE LOGITS
     property
    1.09
     Property
    1.05
    PROPERTY
    0.97
    Property
    0.95
    property
    0.94
     সম্পত্তির
    0.92
    k
    0.92
     PROPERTY
    0.84
    kita
    0.82
     properties
    0.82
    Activations Density 0.038%

    No Known Activations