© 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. 13-GEMMASCOPE-2-RES-16K
    7. 10214
    Prev
    Next
    INDEX
    Explanations

    median calculation, government regulation, market interior

    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_13_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
    तां
    1.98
    ે
    1.94
     Undo
    1.93
    aaaa
    1.92
    𝒉
    1.92
    ଂ
    1.91
    ହା
    1.90
    aaaaaaaa
    1.89
     wcex
    1.87
    ମ୍
    1.86
    POSITIVE LOGITS
    ,
    1.41
    ),
    1.38
    .
    1.35
    )
    1.27
     box
    1.20
     reduce
    1.20
     ,
    1.16
     reduced
    1.15
    ).
    1.15
     ),
    1.15
    Activations Density 0.008%

    No Known Activations