© 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. 10838
    Prev
    Next
    INDEX
    Explanations

    alerts and announcements

    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
    ições
    2.64
    igious
    2.22
    ographics
    2.15
    ぇ
    2.06
    ধ
    2.06
    baix
    2.05
    貌
    2.02
    പാട
    2.02
     fraîche
    2.00
     dispensation
    1.98
    POSITIVE LOGITS
    蜒
    2.53
     ren
    2.38
    dbThoughtData
    2.38
    蛉
    2.32
    ფილი
    2.28
    ndo
    2.26
     spricht
    2.26
     odw
    2.21
     داستان
    2.16
    ෙකු
    2.15
    Activations Density 0.000%

    No Known Activations