Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 6494
    Prev
    Next
    INDEX
    Explanations

    would give, would pose, would be

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
    ﻐ
    1.01
    ﺸ
    0.95
    ﺤ
    0.94
    ﻨ
    0.94
     повышения
    0.93
     Laat
    0.92
     situación
    0.91
     integrado
    0.91
    ﻀ
    0.91
    ﻤ
    0.90
    POSITIVE LOGITS
    مل
    0.90
    টি
    0.86
     diligently
    0.81
    ন
    0.80
    ناس
    0.80
     uniques
    0.77
    people
    0.77
     personnelles
    0.76
    孀
    0.76
    ص
    0.75
    Activations Density 0.000%

    No Known Activations