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. 1043
    Prev
    Next
    INDEX
    Explanations

    2000 word

    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
    がいい
    1.04
    不是
    1.02
    ↵
    1.01
    ل
    1.01
    ری
    1.00
     Embassy
    1.00
    ন
    1.00
    Foo
    0.98
    oretically
    0.97
    s
    0.97
    POSITIVE LOGITS
     있었
    1.10
     últ
    1.07
     хотелось
    1.05
    iendo
    1.05
     собственного
    1.02
     Архиви
    1.01
     желательно
    1.00
     maravilh
    1.00
    tris
    0.99
     связь
    0.99
    Activations Density 0.001%

    No Known Activations