© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 12424
    Prev
    Next
    INDEX
    Explanations

    variable assignment

    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_22_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
    長さ
    0.70
    𝖘
    0.68
     avoir
    0.67
     प्राय
    0.65
     گرف
    0.64
    کسی
    0.64
    क्षि
    0.63
    avoir
    0.62
     forn
    0.61
     گذا
    0.61
    POSITIVE LOGITS
    囱
    0.88
    ugel
    0.82
     রিভিউ
    0.81
    หล
    0.80
     Wesley
    0.78
     entste
    0.78
    oucí
    0.77
    Ҭ
    0.77
     McL
    0.76
     açúcar
    0.75
    Activations Density 0.001%

    No Known Activations