© 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. 40531
    Prev
    Next
    INDEX
    Explanations

    was/is/fue/è followed by an article

    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
    Namun
    1.04
     which
    0.96
    RR
    0.91
    и
    0.91
    which
    0.88
     oedd
    0.86
    所以
    0.84
    Clicked
    0.84
     které
    0.83
    Kil
    0.83
    POSITIVE LOGITS
    ﻜ
    0.99
    ↵↵
    0.95
     một
    0.91
    oyeva
    0.91
    ↵
    0.90
     、,
    0.89
    ogeneous
    0.88
    stays
    0.87
    ean
    0.87
     isang
    0.85
    Activations Density 0.004%

    No Known Activations