© 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. 24-GEMMASCOPE-2-RES-262K
    7. 11231
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_24_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
     deterg
    0.68
     discourse
    0.63
     petition
    0.62
     masse
    0.61
    UTES
    0.61
     sneaker
    0.59
     authorised
    0.59
    岐
    0.59
     Ka
    0.58
     člán
    0.58
    POSITIVE LOGITS
     紹介
    0.75
    사람
    0.71
    য্
    0.70
     ব্যতিক্রম
    0.69
     비교
    0.69
     Же
    0.69
    ailles
    0.68
     пър
    0.67
     약
    0.66
    ⇰
    0.66
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.