© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 10275
    Prev
    Next
    INDEX
    Explanations

    Tagalog linker "ang"

    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_40_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
     теркәлү
    0.54
     Ві
    0.54
     користу
    0.54
     Ergebn
    0.53
     Jodie
    0.53
     фаразлары
    0.53
     ziff
    0.53
    朳
    0.52
     фаразы
    0.51
     selbst
    0.50
    POSITIVE LOGITS
     mga
    0.86
     hindi
    0.77
     isang
    0.76
    Mga
    0.71
     maraming
    0.70
     sa
    0.69
     maaaring
    0.69
     kanilang
    0.69
     kahit
    0.68
     iba
    0.67
    Activations Density 0.002%

    No Known Activations