© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 2150
    Prev
    Next
    INDEX
    Explanations

    increasing prevalence and quantity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
     Helv
    1.76
     Alli
    1.76
     Liss
    1.76
    )])
    1.76
     grove
    1.75
     appointees
    1.75
     paździer
    1.75
    )):
    1.74
    ifed
    1.74
    дел
    1.73
    POSITIVE LOGITS
    很多人
    1.85
    很多的
    1.84
     oftentimes
    1.75
     multitud
    1.59
     often
    1.55
     spesso
    1.53
     many
    1.51
     innumerable
    1.51
     molte
    1.50
    越来越多
    1.44
    Activations Density 0.465%

    No Known Activations