© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 3010
    Prev
    Next
    INDEX
    Explanations

    creating a data structure

    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
    Not in Any Lists

    No Comments

    Negative Logits
    𝙙
    2.94
    a
    2.66
     planta
    2.66
    ಿಗ
    2.66
    淀
    2.61
    おり
    2.55
    idenav
    2.55
    𝙨
    2.54
    angana
    2.52
    nements
    2.52
    POSITIVE LOGITS
    𝐞
    2.90
    ساس
    2.80
    হেন
    2.63
    ला
    2.63
    传统
    2.61
     дописавши
    2.57
    𝐡
    2.56
     MAKEINTRESOURCE
    2.53
    protractor
    2.52
    stein
    2.51
    Activations Density 0.245%

    No Known Activations