© 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. 2692
    Prev
    Next
    INDEX
    Explanations

    contrasting abstract concepts

    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
     whenever
    1.23
     having
    1.23
     roughly
    1.19
     mencionado
    1.19
    <b>
    1.19
    Â
    1.18
     somewhat
    1.17
     Chancery
    1.15
    с
    1.12
     а
    1.10
    POSITIVE LOGITS
    ättre
    1.90
     构建
    1.90
    xcschemes
    1.89
    ਹੀ
    1.89
     regole
    1.86
    geschossiges
    1.86
    ണ്‍
    1.84
    }$&$-
    1.83
    𒆪
    1.82
    िफिशियल
    1.82
    Activations Density 0.410%

    No Known Activations