© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-262K
    7. 149822
    Prev
    Next
    INDEX
    Explanations

    automatically create or manage

    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_29_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
    כה
    0.92
     sevent
    0.85
     Theoretically
    0.84
     Therefore
    0.83
     seventy
    0.83
    一百
    0.81
     seventeenth
    0.80
    ₁
    0.78
     seventeen
    0.78
     hundred
    0.75
    POSITIVE LOGITS
     espe
    0.72
    諰
    0.71
     dyr
    0.71
     dee
    0.70
    䂙
    0.69
    ৃদ্ধ
    0.68
     Orc
    0.68
    郘
    0.68
    dDays
    0.66
    uć
    0.66
    Activations Density 0.000%

    No Known Activations