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-3-12B-IT
    3. 24-GEMMASCOPE-2-RES-16K
    4. 7285
    Prev
    Next
    INDEX
    Explanations

    cancel, remove, delete

    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_24_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
    گار
    0.83
    সজ্জিত
    0.82
    ებისთვის
    0.82
    נים
    0.80
     وکړئ
    0.79
    ਕ
    0.79
    Przyp
    0.78
    кового
    0.77
     outfitted
    0.77
    齐全
    0.75
    POSITIVE LOGITS
     khỏi
    1.20
    掉
    1.13
     removes
    1.05
    掉了
    1.02
     Removes
    0.98
     Removing
    0.98
     deletes
    0.94
     premat
    0.92
     removing
    0.91
     therefrom
    0.89
    Activations Density 1.224%

    No Known Activations