© 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. 22-GEMMASCOPE-2-RES-16K
    7. 8412
    Prev
    Next
    INDEX
    Explanations

    doesn't automatically mean

    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
     Chrome
    1.18
     jQuery
    1.08
     Hickory
    1.07
     木製
    1.04
     AppComponent
    1.03
    <0x94>
    1.03
     browsers
    1.02
    HTMLElement
    1.01
     chrome
    1.00
    橡
    0.99
    POSITIVE LOGITS
    Prison
    1.20
    prisoner
    1.20
    await
    1.17
     prison
    1.11
    prison
    1.09
     Prison
    1.07
    maw
    1.04
    prisoners
    1.04
     await
    1.03
    Serv
    1.01
    Activations Density 0.006%

    No Known Activations