© 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. 10935
    Prev
    Next
    INDEX
    Explanations

    work with

    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
     airs
    0.89
     nook
    0.79
     speedy
    0.77
     ancillary
    0.77
     inventing
    0.77
    ે
    0.75
    க்கை
    0.74
     fridge
    0.73
     woll
    0.73
    ্বের
    0.73
    POSITIVE LOGITS
    ის
    1.02
    ons
    0.98
    ka
    0.93
    та
    0.92
    re
    0.91
     që
    0.91
    ած
    0.89
     tudi
    0.89
    讯
    0.89
    to
    0.88
    Activations Density 0.004%

    No Known Activations