© 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. 12-GEMMASCOPE-2-RES-16K
    7. 3328
    Prev
    Next
    INDEX
    Explanations

    millions of parameters, billions of 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_12_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
    wb
    1.08
    0
    1.08
     temporada
    1.01
    WB
    1.00
    6
    0.97
    BAN
    0.94
     Anzahl
    0.92
    9
    0.92
    emura
    0.91
     rodzaju
    0.90
    POSITIVE LOGITS
     mile
    1.75
     painfully
    1.66
     dement
    1.58
     curly
    1.57
     miles
    1.56
     painstakingly
    1.55
     hale
    1.55
     miraculously
    1.55
     garg
    1.55
     blurry
    1.54
    Activations Density 0.217%

    No Known Activations