© 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. 9-GEMMASCOPE-2-RES-262K
    7. 10100
    Prev
    Next
    INDEX
    Explanations

    favorite, flavors, fiber, favors

    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_9_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
    ia
    3.69
    ie
    3.55
    ندگان
    3.34
    ية
    3.34
    й
    3.30
    д
    3.21
    м
    3.17
    م
    3.17
    न
    3.15
    िक
    3.14
    POSITIVE LOGITS
    ()=>{
    4.09
    𝚐
    3.48
    ти
    3.26
    𝐡
    3.22
    して
    3.21
    のが
    3.11
    𝘦
    3.08
    indest
    3.07
    ्री
    3.05
    '%
    3.01
    Activations Density 0.613%

    No Known Activations