© 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. 7834
    Prev
    Next
    INDEX
    Explanations

    police action and arrests

    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
     kors
    0.91
     isos
    0.91
     Versicher
    0.91
    ிகள்
    0.90
    償
    0.90
     ymp
    0.88
     stry
    0.86
     incest
    0.86
     Lloyd
    0.86
     Melan
    0.86
    POSITIVE LOGITS
     arrest
    1.66
     arrests
    1.57
    arrest
    1.50
     arresting
    1.38
     search
    1.35
     Arrest
    1.33
    Sear
    1.32
    sear
    1.32
    搜
    1.32
     Search
    1.31
    Activations Density 0.224%

    No Known Activations