© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 965
    Prev
    Next
    INDEX
    Explanations

    showing evidence or capabilities

    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
    笛
    1.13
    aphor
    1.12
     Gramm
    1.06
    getter
    1.05
    具体的
    1.05
     abstracto
    1.04
    roller
    1.03
    lak
    1.03
    かん
    1.03
     ::=
    1.03
    POSITIVE LOGITS
     shows
    2.90
     show
    2.83
     showing
    2.83
    shows
    2.73
    showing
    2.73
     showed
    2.62
    show
    2.60
     Shows
    2.59
    显示
    2.58
    顯示
    2.54
    Activations Density 1.083%

    No Known Activations