© 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. 99373
    Prev
    Next
    INDEX
    Explanations

    numbers with units or symbols

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

    mathematical notation `\, dt`

    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
     y
    0.54
     see
    0.51
    ild
    0.51
     n
    0.50
    ini
    0.50
    za
    0.50
     lento
    0.49
     punto
    0.49
     resource
    0.49
     ip
    0.48
    POSITIVE LOGITS
    洌
    0.49
    энд
    0.48
    禣
    0.47
    㑨
    0.45
    үндө
    0.44
    ','"
    0.43
     StatusBar
    0.43
     противоре
    0.43
     স্যা
    0.42
     измерения
    0.42
    Activations Density 0.000%

    No Known Activations