Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-16K
    4. 7295
    Prev
    Next
    INDEX
    Explanations

    refusal to provide instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_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
     إليه
    0.86
     attempt
    0.77
     Attempt
    0.73
     एक्सपे
    0.73
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.72
    움을
    0.71
     различными
    0.71
     попы
    0.71
    വരെ
    0.71
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.70
    POSITIVE LOGITS
    il
    0.79
    on
    0.78
     conosce
    0.78
    nei
    0.74
    uko
    0.73
     khan
    0.69
    <?
    0.68
    नियर
    0.68
    𝑮
    0.67
    щих
    0.67
    Activations Density 0.026%

    No Known Activations