© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 4222
    Prev
    Next
    INDEX
    Explanations

    installing or opening code

    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
     (#{
    1.15
    RuL
    1.10
    ❝
    1.04
     unwell
    1.03
    нев
    1.03
    あれ
    1.02
    nativeElement
    1.02
    akoti
    1.00
    тися
    1.00
     '${
    0.99
    POSITIVE LOGITS
     soundtracks
    1.66
     glaz
    1.40
    semantics
    1.37
     IBA
    1.34
    رین
    1.34
    epid
    1.33
     soundtrack
    1.33
     banderas
    1.33
    tikz
    1.32
     chans
    1.32
    Activations Density 0.011%

    No Known Activations