© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 54575
    Prev
    Next
    INDEX
    Explanations

    different languages for "or"

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     strikingly
    0.51
    டிக்க
    0.48
     remarkably
    0.45
    же
    0.43
    Reactor
    0.43
    ◸
    0.43
    Entrepreneur
    0.43
    著
    0.43
    يهم
    0.42
    نيا
    0.42
    POSITIVE LOGITS
     eller
    0.54
     หรือ
    0.50
     किंवा
    0.47
     ถ
    0.47
     αντί
    0.47
     alternativa
    0.45
     ज्ञान
    0.44
     또는
    0.44
     biopsies
    0.44
    aped
    0.44
    Activations Density 0.001%

    No Known Activations