© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 12800
    Prev
    Next
    INDEX
    Explanations

    phrases mixing languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_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
     (
    1.32
     (‘
    1.26
    wordpress
    1.24
     കഴിയ
    1.22
    indices
    1.20
    permission
    1.20
    AdapterView
    1.18
    recipe
    1.18
    Checker
    1.18
    ίνη
    1.18
    POSITIVE LOGITS
     Emphasis
    1.53
    糈
    1.53
    dR
    1.52
    णीय
    1.51
    湎
    1.50
    تال
    1.49
     António
    1.47
    堞
    1.45
    iß
    1.45
    欤
    1.44
    Activations Density 0.000%

    No Known Activations