© 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. 10920
    Prev
    Next
    INDEX
    Explanations

    stocks on the FTSE

    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
    м
    1.56
    voorbeeld
    1.29
    lia
    1.15
    дро
    1.14
    жно
    1.14
    lapse
    1.13
    лес
    1.13
    l
    1.11
    ва
    1.09
    िश
    1.07
    POSITIVE LOGITS
     martyrs
    1.36
     ημέ
    1.32
    electricity
    1.28
     comun
    1.27
     announc
    1.25
     axonal
    1.25
     পুর্ব
    1.25
     depl
    1.24
     blistering
    1.23
     diaphragm
    1.23
    Activations Density 0.000%

    No Known Activations