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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 3639
    Prev
    Next
    INDEX
    Explanations

    **beginning/introduction words**

    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
    ات
    0.98
    ের
    0.86
    ли
    0.82
    ுள்ளது
    0.81
    ب
    0.81
    した
    0.81
     인한
    0.80
    ても
    0.79
    อะคาเดมี
    0.79
    આ
    0.79
    POSITIVE LOGITS
    HIB
    0.78
    وانات
    0.77
    asının
    0.76
    ROWS
    0.76
    мові
    0.75
     первые
    0.73
     khẳng
    0.72
    ви
    0.72
    o
    0.72
    Ht
    0.71
    Activations Density 0.526%

    No Known Activations