© 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-65K
    7. 6936
    Prev
    Next
    INDEX
    Explanations

    ordering, ranking, sorting

    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_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
    螨
    0.74
    蟎
    0.70
    awning
    0.68
     forg
    0.66
    Forg
    0.65
     Mueller
    0.65
    mongoUrl
    0.64
    阱
    0.63
     pleinement
    0.63
     infiltrated
    0.63
    POSITIVE LOGITS
     ranking
    2.73
    排序
    2.60
     Ranking
    2.58
     rankings
    2.54
     ordering
    2.51
    Ranking
    2.50
     order
    2.50
     ranked
    2.48
     Ranked
    2.36
     Ordering
    2.29
    Activations Density 0.748%

    No Known Activations