© 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. 13865
    Prev
    Next
    INDEX
    Explanations

    economics and finance

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

    economic terms and costs

    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
    translational
    0.50
     příst
    0.48
     práv
    0.47
    Preprocessor
    0.46
    CrossOrigin
    0.45
     Israël
    0.45
     Surreal
    0.45
    ⵉ
    0.45
    ⵣ
    0.44
    ന്ദ്ര
    0.44
    POSITIVE LOGITS
     justly
    0.41
     average
    0.41
     automobile
    0.41
     locomotive
    0.40
     влия
    0.40
     tend
    0.40
    fee
    0.40
    工资
    0.39
    §
    0.39
     increase
    0.39
    Activations Density 0.006%

    No Known Activations