© 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. 10465
    Prev
    Next
    INDEX
    Explanations

    numbered lists and titles

    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
     structurally
    1.06
    로
    1.04
    ավոր
    1.02
    ের
    1.01
    angles
    1.01
    як
    1.00
     proponents
    1.00
    აკ
    1.00
    ना
    0.99
    で
    0.99
    POSITIVE LOGITS
    সজ্জিত
    1.14
    er
    1.10
    spaper
    1.07
    ν
    1.05
     말미암아
    1.04
    hyd
    1.04
    hasta
    1.03
     bagay
    1.02
     gyr
    0.99
     jedem
    0.99
    Activations Density 0.666%

    No Known Activations