© 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-3-4B
    5. 29-GEMMASCOPE-2-RES-16K
    7. 1839
    Prev
    Next
    INDEX
    Explanations

    3D space

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-pt/resid_post/layer_29_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
     десять
    0.94
     восем
    0.94
     шесть
    0.87
     девя
    0.83
     oito
    0.83
     četiri
    0.80
     zehn
    0.80
    <sub>
    0.79
     четыре
    0.79
     пять
    0.78
    POSITIVE LOGITS
     $$$
    0.72
     double
    0.68
     ½
    0.66
     +/-
    0.66
     semi
    0.64
     +-
    0.63
     bulky
    0.62
     overhead
    0.62
     evt
    0.62
     unlimited
    0.61
    Activations Density 0.222%

    No Known Activations