© 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. 9410
    Prev
    Next
    INDEX
    Explanations

    print statement

    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
    েরই
    1.07
     Metall
    1.01
    }^{-}
    0.99
    bend
    0.97
    oleh
    0.96
    របស់
    0.96
    oxyd
    0.95
    മായി
    0.94
    rukh
    0.94
    ,’”
    0.94
    POSITIVE LOGITS
     /></
    1.05
     />
    0.92
     />,
    0.90
     />}></
    0.87
     load
    0.85
     sürü
    0.85
     sür
    0.85
    </blockquote>
    0.84
     loading
    0.83
     /><
    0.83
    Activations Density 0.005%

    No Known Activations