© 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. 29-GEMMASCOPE-2-RES-65K
    7. 2262
    Prev
    Next
    INDEX
    Explanations

    well, smoothly, poorly

    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_65k_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
    屉
    0.67
    ᑎ
    0.64
    reachable
    0.61
    денциа
    0.61
    攢
    0.60
     подвер
    0.60
    ຕິດຕໍ່
    0.58
    䒑
    0.58
    NotIn
    0.58
    ậm
    0.58
    POSITIVE LOGITS
     well
    4.16
    well
    3.34
     Well
    3.17
    Well
    3.15
     excellently
    3.09
     хорошо
    3.04
     nicely
    3.01
     dobrze
    2.95
     WELL
    2.95
     잘
    2.93
    Activations Density 1.020%

    No Known Activations