© 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. 3623
    Prev
    Next
    INDEX
    Explanations

    .then, .catch

    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
     even
    1.72
    ch
    1.62
     D
    1.50
    aug
    1.49
     U
    1.47
     table
    1.44
     chast
    1.43
     midnight
    1.43
     Even
    1.42
     hours
    1.41
    POSITIVE LOGITS
     jossa
    2.58
     ktorá
    2.45
     współpr
    2.45
     puriso
    2.39
    竻
    2.37
    嵃
    2.35
    上で
    2.30
     koci
    2.26
    سازی
    2.25
     cocok
    2.24
    Activations Density 0.152%

    No Known Activations