© 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. 227861
    Prev
    Next
    INDEX
    Explanations

    non-english and common words

    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
     फायदा
    0.50
    VARIABLES
    0.48
    [:
    0.44
    jpe
    0.44
     حوالے
    0.44
     promedio
    0.43
     colocar
    0.43
    قبل
    0.43
     reú
    0.43
    いずれ
    0.43
    POSITIVE LOGITS
     Cust
    0.50
    τισ
    0.46
    स्व
    0.45
    ᴼ
    0.45
    לב
    0.44
     advoc
    0.44
    optera
    0.44
     lymphoid
    0.44
     ओलंपिक
    0.43
    τια
    0.43
    Activations Density 0.000%

    No Known Activations