© 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. 1491
    Prev
    Next
    INDEX
    Explanations

    age in years

    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
     중심
    1.23
     StandardScaler
    1.17
    κή
    1.10
     рэ
    1.07
     sistem
    1.04
    ベー
    1.01
    かん
    1.01
    믈
    1.00
    āv
    0.98
     şə
    0.98
    POSITIVE LOGITS
    years
    2.77
    yrs
    2.60
     yrs
    2.51
     years
    2.50
     años
    2.28
    year
    2.28
     YEARS
    2.26
     Years
    2.10
     سنوات
    2.10
    Years
    2.09
    Activations Density 0.413%

    No Known Activations