© 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. 22-GEMMASCOPE-2-RES-16K
    7. 7945
    Prev
    Next
    INDEX
    Explanations

    energy density

    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_22_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
     tuttavia
    1.41
     ș
    1.32
     nonprofit
    1.32
     számos
    1.29
     backcountry
    1.27
     neighborhoods
    1.26
     gerenci
    1.26
     matchup
    1.24
    чён
    1.23
     zaten
    1.23
    POSITIVE LOGITS
     Gandhiji
    1.54
     upto
    1.42
     Nagpur
    1.31
    organisation
    1.29
    ⟋
    1.28
     organisation
    1.27
    centres
    1.24
     Lucknow
    1.21
    programme
    1.18
    centre
    1.15
    Activations Density 0.068%

    No Known Activations