© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 2026
    Prev
    Next
    INDEX
    Explanations

    re- + action verbs

    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
    zes
    1.91
    スプレイ
    1.79
    睺
    1.71
    tes
    1.69
    ttes
    1.66
    keun
    1.63
    тво
    1.60
    cs
    1.57
    kie
    1.52
     femenino
    1.52
    POSITIVE LOGITS
    ן
    2.25
    潦
    2.06
     render
    2.05
     appren
    2.05
     apprend
    2.05
     મિત
    2.04
     ပဲ
    2.02
    горь
    2.01
     Blockchain
    2.00
     GitHub
    2.00
    Activations Density 0.018%

    No Known Activations