© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 1255
    Prev
    Next
    INDEX
    Explanations

    Arabic conjunction 'wa' or 'wal'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_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
    nob
    0.83
    s
    0.80
     inquirer
    0.77
    放題
    0.73
     officielle
    0.72
    maj
    0.72
    мя
    0.71
    isimple
    0.69
    neb
    0.69
     অশ্র
    0.69
    POSITIVE LOGITS
     alert
    0.79
     Greyhound
    0.76
    Emer
    0.74
    өл
    0.74
     ইঞ্জিনিয়ার
    0.73
    篪
    0.73
    ijke
    0.72
    বা
    0.72
     документи
    0.72
     sequels
    0.72
    Activations Density 0.005%

    No Known Activations