© 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. 70447
    Prev
    Next
    INDEX
    Explanations

    Tax Credit and earnings

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

    language games

    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
     Naam
    0.47
     Describes
    0.44
     Precipitation
    0.44
    ExpressCheckout
    0.43
    egin
    0.41
    əsi
    0.41
    [],
    0.41
     sə
    0.41
    гем
    0.40
    łka
    0.40
    POSITIVE LOGITS
    রির
    0.52
     כדי
    0.48
    間で
    0.48
     ridiculously
    0.47
     положения
    0.47
    家伙
    0.47
     नाराजगी
    0.46
     obnoxious
    0.45
     networking
    0.44
     grocery
    0.44
    Activations Density 0.000%

    No Known Activations