© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 1424
    Prev
    Next
    INDEX
    Explanations

    ever or never past experiences

    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_16k_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
     yeni
    0.79
     new
    0.77
    全新的
    0.76
    新的
    0.75
    ့
    0.74
    新たな
    0.74
     본격
    0.72
     nuovi
    0.71
     الجديدة
    0.71
    க்குள்
    0.71
    POSITIVE LOGITS
     pernah
    2.57
    เคย
    2.43
     เคย
    2.14
    曾在
    1.90
    曾經
    1.87
    曾
    1.79
    几次
    1.75
    多次
    1.75
     occasions
    1.70
     ocasiones
    1.68
    Activations Density 0.483%

    No Known Activations