© 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. 5298
    Prev
    Next
    INDEX
    Explanations

    at [entity name]

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

    rates, percentages, and money

    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
    ILI
    0.41
     liệt
    0.40
    alke
    0.40
     يُ
    0.38
    朗
    0.38
     მხ
    0.38
     மக்கள
    0.38
    羥
    0.38
    Fl
    0.36
     श्रीवास्तव
    0.36
    POSITIVE LOGITS
     investimento
    0.54
     a
    0.54
     an
    0.45
     beserta
    0.44
     condiciones
    0.43
     semej
    0.42
     inputted
    0.42
     investimentos
    0.42
     agar
    0.41
    investment
    0.41
    Activations Density 0.000%

    No Known Activations