© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 6968
    Prev
    Next
    INDEX
    Explanations

    to + verb actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
    dí
    1.02
     normales
    0.98
     obligatorio
    0.98
    馨
    0.97
    展望
    0.97
     norma
    0.96
    条例
    0.94
    に戻
    0.93
    Should
    0.93
     evils
    0.91
    POSITIVE LOGITS
     conseguiu
    2.43
    鍥
    2.37
    Persistence
    2.32
     convain
    2.28
     logró
    2.27
     convincing
    2.27
     linkedin
    2.17
     consiguió
    2.15
     luckily
    2.11
     persuading
    2.10
    Activations Density 0.224%

    No Known Activations