© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 16-GEMMASCOPE-2-RES-16K
    7. 708
    Prev
    Next
    INDEX
    Explanations

    Foreign word stems and suffixes

    np_acts-logits-general · gemini-2.5-flash-lite

    word completion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_16_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    an
    1.48
    ia
    1.48
    am
    1.35
    ik
    1.32
    ab
    1.24
    ap
    1.18
     can
    1.14
    um
    1.11
    на
    1.09
    c
    1.09
    POSITIVE LOGITS
    2
    1.27
    4
    1.27
    8
    1.26
    5
    1.22
    9
    1.17
    ς
    1.09
    ਆਂ
    1.05
    7
    1.02
    ের
    1.02
    '
    1.00
    Activations Density 0.089%

    No Known Activations