© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 17-GEMMASCOPE-2-RES-16K
    7. 7453
    Prev
    Next
    INDEX
    Explanations

    seconds and hours

    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
    <0x95>
    0.91
     വഴ
    0.88
    7
    0.82
    ानु
    0.81
     hoặc
    0.80
    6
    0.78
    9
    0.78
    堑
    0.77
    ्री
    0.77
    QUEST
    0.76
    POSITIVE LOGITS
     synonymous
    0.91
     İlçesi
    0.89
    -"
    0.85
     लिमिटेड
    0.83
     acumen
    0.82
    ちゃんの
    0.82
     edilen
    0.81
     ஆண்டில்
    0.81
    ﹊
    0.80
    𒈗
    0.80
    Activations Density 0.441%

    No Known Activations