© 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. 13972
    Prev
    Next
    INDEX
    Explanations

    phrases describing something

    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
     Hammer
    0.83
     Monk
    0.78
    ॐ
    0.76
     Napoli
    0.74
     bombas
    0.71
    ρευ
    0.70
     Trojan
    0.69
     keV
    0.69
    菪
    0.69
     useNewUrlParser
    0.68
    POSITIVE LOGITS
     XHTML
    0.90
     उत्तरा
    0.74
     limousine
    0.72
    䢍
    0.72
    赅
    0.71
     Tweed
    0.71
    מין
    0.70
     división
    0.69
     हिमा
    0.69
    平面
    0.68
    Activations Density 0.000%

    No Known Activations