© 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-262K
    7. 11610
    Prev
    Next
    INDEX
    Explanations

    Here's a breakdown

    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
    ت
    1.60
    تف
    1.60
    aço
    1.55
     tions
    1.53
    iovascular
    1.48
    ροι
    1.43
     उन्होंने
    1.42
    рованию
    1.42
    tır
    1.42
    eris
    1.39
    POSITIVE LOGITS
    அல்ல
    1.62
     FirstName
    1.36
    .:
    1.30
     таки
    1.29
     sinner
    1.21
    шку
    1.20
     something
    1.17
     nh
    1.15
     باشید
    1.15
     Hatter
    1.13
    Activations Density 0.480%

    No Known Activations