© 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. 16311
    Prev
    Next
    INDEX
    Explanations

    list item indicators

    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
    0.79
     agua
    0.79
     v
    0.78
     wetlands
    0.78
     por
    0.78
     triangle
    0.77
     preg
    0.77
     sedan
    0.77
     bread
    0.76
     cat
    0.74
    POSITIVE LOGITS
    theless
    1.09
    oubtedly
    1.02
    ljeni
    1.01
    Issued
    0.98
    ӣ
    0.95
    ವೀ
    0.94
    munk
    0.94
    ritu
    0.93
    oraj
    0.93
     unworthy
    0.92
    Activations Density 0.194%

    No Known Activations