© 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. 242
    Prev
    Next
    INDEX
    Explanations

    code snippets and explanations

    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
    s
    1.15
    ्स
    1.00
    ДА
    1.00
    ﺮ
    0.99
    ्ट
    0.98
     巴
    0.96
    ТА
    0.95
    いたり
    0.90
    ের
    0.89
     অক্টোবর
    0.89
    POSITIVE LOGITS
     seit
    1.09
    −−
    1.05
    ✶
    1.04
    ✔️
    0.99
     Claremont
    0.96
     debe
    0.96
    
    0.94
    <0xCA>
    0.93
    querdo
    0.93
    larından
    0.93
    Activations Density 0.565%

    No Known Activations