© 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. 30932
    Prev
    Next
    INDEX
    Explanations

    Johnson & Johnson, Unilever, P&G

    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
     এছাড়াও
    1.13
                
    1.07
    Эк
    1.03
    哥哥
    1.00
    疯狂
    0.99
    است
    0.96
    Easter
    0.95
     '@/
    0.95
    0.95
    欧洲
    0.94
    POSITIVE LOGITS
    an
    1.48
    з
    1.41
     krwi
    1.41
    er
    1.36
    ด์
    1.36
    heet
    1.32
    z
    1.30
    น
    1.30
    and
    1.28
    ية
    1.28
    Activations Density 0.002%

    No Known Activations