© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 14338
    Prev
    Next
    INDEX
    Explanations

    Middle East, digital, individuals advocating

    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
    lovely
    1.59
     impoverished
    1.42
    𝑎
    1.41
    ća
    1.38
    𝑚
    1.38
    𝑣
    1.37
    endet
    1.37
    𝑝
    1.37
    cts
    1.36
    ナソニック
    1.35
    POSITIVE LOGITS
    ഴ്ച
    1.07
     tril
    1.05
     hxg
    1.04
     geral
    1.01
     thế
    1.01
    eep
    0.99
     ​​
    0.97
    வே
    0.92
    Fprintf
    0.92
    ์
    0.92
    Activations Density 0.000%

    No Known Activations