© 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. 7-GEMMASCOPE-2-RES-16K
    7. 2762
    Prev
    Next
    INDEX
    Explanations

    a little Japanese; patchwork appearance

    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_7_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
    KEYDOWN
    2.04
    ́t
    2.02
    aturated
    2.00
    ́u
    1.95
    amples
    1.91
     टाइम्स
    1.89
     Darstellung
    1.89
    (_.
    1.88
     мно
    1.87
    ployment
    1.85
    POSITIVE LOGITS
    ty
    2.22
    ism
    2.17
    ted
    2.10
    সি
    2.04
    ર
    2.01
    er
    1.96
    ta
    1.94
    tra
    1.89
    م
    1.89
    िंग
    1.88
    Activations Density 0.008%

    No Known Activations