© 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. 11390
    Prev
    Next
    INDEX
    Explanations

    URLs and URIs

    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
    taine
    1.43
    ं
    1.40
    ﹰ
    1.38
    tedir
    1.37
    
    1.35
     $^{\
    1.30
    blastoma
    1.30
     militar
    1.29
    ت
    1.28
     Corollary
    1.28
    POSITIVE LOGITS
     pudd
    1.39
    ierung
    1.26
     finde
    1.26
     dispoz
    1.25
    ente
    1.25
     toepassing
    1.23
     creo
    1.23
    hibition
    1.22
    有很多
    1.21
    varande
    1.20
    Activations Density 0.001%

    No Known Activations