© 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-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 42488
    Prev
    Next
    INDEX
    Explanations

    imitation learning

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_16_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
     trueMap
    0.92
     allemand
    0.88
     immobili
    0.88
     และ
    0.84
     esegu
    0.83
    ﺍ
    0.83
     וה
    0.83
     synthes
    0.82
     spineItem
    0.82
     and
    0.82
    POSITIVE LOGITS
    it
    1.42
    ور
    1.08
    our
    1.05
    at
    0.97
    ם
    0.96
    ut
    0.91
    arr
    0.90
    *}$
    0.90
    ა
    0.90
    ri
    0.89
    Activations Density 0.002%

    No Known Activations