© 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. 9-GEMMASCOPE-2-RES-16K
    7. 2247
    Prev
    Next
    INDEX
    Explanations

    SaaS lifetime, shortness of breath, breach

    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_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
    ့
    3.71
    臾
    3.59
     불구하고
    3.50
     destinés
    3.39
    ंपल
    3.29
     atât
    3.26
    ্ধ্য
    3.23
     ylabel
    3.16
    특별시
    3.12
     dtype
    3.07
    POSITIVE LOGITS
    ت
    4.06
    н
    3.98
    ה
    3.76
    ン
    3.65
    s
    3.65
    т
    3.53
    ра
    3.29
    an
    3.25
    ет
    3.25
    берите
    3.20
    Activations Density 0.459%

    No Known Activations