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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-16K
    4. 1889
    Prev
    Next
    INDEX
    Explanations

    why did

    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_16k_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
    ت
    1.17
    ن
    1.00
    تون
    0.86
    ни
    0.85
    ش
    0.84
    تان
    0.81
    ل
    0.81
    いや
    0.80
    نا
    0.78
    ת
    0.77
    POSITIVE LOGITS
    ंग्रेस
    1.09
    iguous
    1.00
    aternion
    1.00
    ientras
    0.98
    ṑ
    0.98
    cieron
    0.98
    ௐ
    0.97
    inase
    0.96
    ल्पनिक
    0.96
    gador
    0.94
    Activations Density 0.004%

    No Known Activations