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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 13643
    Prev
    Next
    INDEX
    Explanations

    on, off, false, 0, 5

    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_22_width_262k_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
     textColor
    1.33
    ও
    1.30
     granularity
    1.29
     autophagy
    1.28
     Schrift
    1.27
    ة
    1.25
     sane
    1.25
    𝙀
    1.24
     hexane
    1.22
     penurunan
    1.22
    POSITIVE LOGITS
    ================
    1.93
    ===============
    1.58
    ͟
    1.43
    ⿺
    1.35
    *",
    1.34
    ()=>{
    1.33
    false
    1.32
    ‖</
    1.32
    ============
    1.31
    ্ট
    1.30
    Activations Density 0.030%

    No Known Activations