© 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-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 251
    Prev
    Next
    INDEX
    Explanations

    but introducing contrast

    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_17_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
    াল
    0.65
    ри
    0.61
    े
    0.59
    у
    0.57
    ше
    0.57
     tedy
    0.56
    ح
    0.53
    и
    0.51
    在
    0.50
    как
    0.48
    POSITIVE LOGITS
    thole
    0.85
    termilk
    0.83
     néanmoins
    0.83
     nevertheless
    0.82
     nonetheless
    0.80
     dennoch
    0.76
     alas
    0.72
     digress
    0.64
    tered
    0.62
     luckily
    0.62
    Activations Density 0.574%

    No Known Activations