© 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. 5982
    Prev
    Next
    INDEX
    Explanations

    hexadecimal and numeric strings

    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
    itev
    0.70
    <unused1799>
    0.69
    <unused2146>
    0.68
    <unused985>
    0.67
    KV
    0.65
     удаления
    0.65
    ️⃣
    0.65
    <unused1216>
    0.65
    <unused1093>
    0.64
    bathy
    0.63
    POSITIVE LOGITS
    し
    0.69
     hypertext
    0.64
     perfusion
    0.64
    その
    0.63
    Интернет
    0.63
     phon
    0.61
     ప్రజ
    0.61
    你
    0.61
     collo
    0.59
     slightest
    0.58
    Activations Density 0.082%

    No Known Activations