© 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. 13420
    Prev
    Next
    INDEX
    Explanations

    process or technical terms

    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
     both
    0.78
     merged
    0.69
     overarching
    0.68
     fused
    0.68
     submerged
    0.68
    <unused588>
    0.67
     centralised
    0.67
    ‌ی
    0.67
    enums
    0.66
    ₲
    0.66
    POSITIVE LOGITS
    spaper
    1.03
    或
    1.00
    这些
    0.96
    flake
    0.93
    k
    0.92
     गुना
    0.91
     सिसोदिया
    0.89
    TP
    0.88
    減少
    0.88
     এসব
    0.87
    Activations Density 0.515%

    No Known Activations