© 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. 11507
    Prev
    Next
    INDEX
    Explanations

    calculating maximum values

    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
    Diff
    1.39
    Maker
    1.36
    яв
    1.33
    പ
    1.29
    payer
    1.27
    र्घ
    1.26
    CEL
    1.26
    matics
    1.25
    publish
    1.24
    𝑒
    1.20
    POSITIVE LOGITS
     didik
    1.97
     trabalhadores
    1.95
     akik
    1.88
     okula
    1.75
    들에게
    1.74
     regiments
    1.73
     mobilize
    1.72
     trabajadores
    1.71
     arkadaşlar
    1.67
     którzy
    1.65
    Activations Density 0.143%

    No Known Activations