© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 13747
    Prev
    Next
    INDEX
    Explanations

    Resource Owner, MouseOver, either/both

    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
     Oh
    0.91
     M
    0.82
     Cro
    0.80
     OH
    0.79
     Ce
    0.78
     oh
    0.77
     م
    0.77
    as
    0.76
     F
    0.74
     Q
    0.74
    POSITIVE LOGITS
     både
    1.22
    Both
    1.11
    दोनों
    1.10
    BOTH
    1.00
     sowohl
    0.98
    assertEquals
    0.94
    Trước
    0.94
     phục
    0.92
    Either
    0.92
    Debit
    0.92
    Activations Density 0.458%

    No Known Activations