© 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-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 9604
    Prev
    Next
    INDEX
    Explanations

    word endings

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

    words ending in ing

    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_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ot
    0.53
    s
    0.52
    ra
    0.50
    uuml
    0.44
    ase
    0.43
    r
    0.43
    0
    0.43
    ara
    0.42
     Ä
    0.42
    os
    0.42
    POSITIVE LOGITS
     σε
    0.57
     in
    0.53
    在
    0.52
     or
    0.52
     and
    0.48
    ও
    0.45
    도
    0.43
     في
    0.42
    োজ
    0.42
     বা
    0.42
    Activations Density 0.582%

    No Known Activations