© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 12524
    Prev
    Next
    INDEX
    Explanations

    `.py` file extensions

    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
     deteriorated
    1.28
    ☠
    1.27
     fatally
    1.26
     severely
    1.25
     deaths
    1.24
     suffered
    1.24
     killed
    1.23
     fatalities
    1.20
    💔
    1.19
     falleció
    1.18
    POSITIVE LOGITS
     preprocessing
    1.53
     coalgebras
    1.46
     coalgebra
    1.37
     bimodule
    1.35
     membangun
    1.32
     MediaType
    1.32
     laboratoires
    1.31
     costru
    1.30
    建设
    1.29
     nonEmpty
    1.29
    Activations Density 0.063%

    No Known Activations