© 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. 7116
    Prev
    Next
    INDEX
    Explanations

    name is or isn

    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
     pewno
    1.25
    !!!!!!!!!!!!!!!!
    1.17
    шое
    1.16
    ην
    1.14
     precipit
    1.14
    Ext
    1.13
    ↓↓
    1.13
    受到了
    1.12
     tragen
    1.12
     теперь
    1.12
    POSITIVE LOGITS
     Newell
    1.34
    gate
    1.31
     keynote
    1.29
    insular
    1.25
    ualan
    1.25
    衛
    1.23
     commissary
    1.21
     nasi
    1.21
     maig
    1.19
    vestre
    1.19
    Activations Density 0.019%

    No Known Activations