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. 8418
    Prev
    Next
    INDEX
    Explanations

    diversity and inclusion initiatives

    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
    AN
    2.16
    ных
    2.09
    ON
    2.02
    Elsewhere
    1.98
     novoProduto
    1.95
    َ
    1.89
    ்
    1.86
    ні
    1.85
    ISTIC
    1.83
    َان
    1.82
    POSITIVE LOGITS
    ни
    2.00
     Dare
    1.96
     уж
    1.90
    ৪
    1.89
     inquire
    1.87
     Aria
    1.87
     melanogaster
    1.85
     Emails
    1.80
    মূলক
    1.77
    ли
    1.74
    Activations Density 0.023%

    No Known Activations