© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 22-GEMMASCOPE-2-RES-16K
    7. 10545
    Prev
    Next
    INDEX
    Explanations

    you know

    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
     propaganda
    1.17
     EXCEPT
    1.16
     except
    1.16
     disconnect
    1.12
     specific
    1.10
    >?
    1.10
     cheat
    1.10
     trucks
    1.09
     無
    1.08
    ?)
    1.07
    POSITIVE LOGITS
    <h1>
    1.00
    úrese
    0.96
     sintomas
    0.93
    。【
    0.89
    ignac
    0.89
     কারনে
    0.87
    atasi
    0.87
    Symptoms
    0.86
    âmara
    0.84
     কারণে
    0.84
    Activations Density 0.028%

    No Known Activations