© 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-16K
    7. 3646
    Prev
    Next
    INDEX
    Explanations

    previous context

    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
    ა
    2.86
    ро
    2.34
    ли
    2.14
    ри
    2.14
    <0x80>
    2.13
    ర్
    2.06
    が変わ
    2.00
    েন
    1.95
    ンジ
    1.95
     trứng
    1.88
    POSITIVE LOGITS
    ا
    2.06
    ج
    2.05
    THING
    1.95
    い
    1.84
     तौर
    1.78
    ig
    1.77
    После
    1.77
    ことになる
    1.76
    rs
    1.73
    sing
    1.67
    Activations Density 0.101%

    No Known Activations