© 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
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 85710
    Prev
    Next
    INDEX
    Explanations

    dividing into halves or parts

    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
    l
    0.93
    g
    0.71
    h
    0.69
    _{
    0.63
    G
    0.60
    al
    0.59
    л
    0.58
     ofthe
    0.57
    j
    0.57
    is
    0.56
    POSITIVE LOGITS
    splitter
    0.62
     دانشج
    0.59
     probative
    0.58
    اضره
    0.57
     দেখলে
    0.56
     dragonfly
    0.55
    เสีย
    0.54
     tenacity
    0.54
    ตัว
    0.53
     jenis
    0.53
    Activations Density 0.009%

    No Known Activations