© 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. 6283
    Prev
    Next
    INDEX
    Explanations

    weaknesses, significance

    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
     대하여
    2.06
    餮
    1.88
    ётся
    1.85
    하였
    1.84
     Всё
    1.82
     Și
    1.81
     이야기
    1.81
     определён
    1.80
    щён
    1.80
     oftentimes
    1.79
    POSITIVE LOGITS
     maths
    1.44
     £
    1.42
     Maths
    1.36
     fertilisers
    1.34
     organising
    1.33
     fertiliser
    1.32
    £
    1.31
     metres
    1.26
     privatisation
    1.26
     UK
    1.25
    Activations Density 0.021%

    No Known Activations