© 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-3-12B-IT
    5. 12-GEMMASCOPE-2-RES-262K
    7. 3891
    Prev
    Next
    INDEX
    Explanations

    call to action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_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
     hues
    1.23
    ↵
    1.13
     ture
    1.09
     quirks
    1.03
     cultures
    1.02
     fielding
    1.02
     follicles
    1.01
    '
    1.01
     innings
    1.00
     inks
    1.00
    POSITIVE LOGITS
    ”).
    1.04
    lian
    0.96
    owymi
    0.95
    )”.
    0.95
    syscall
    0.95
    ).[
    0.94
    apadani
    0.91
    ).”
    0.91
    lardan
    0.90
    сцю
    0.90
    Activations Density 0.111%

    No Known Activations