© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 14398
    Prev
    Next
    INDEX
    Explanations

    questions starting with why

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    栳
    -2.27
    毉
    -2.27
    และ
    -2.27
    
    -2.25
    臵
    -2.16
    ཫ
    -2.13
    
    -2.09
    倧
    -2.09
     bardzo
    -2.08
    柔らかい
    -2.08
    POSITIVE LOGITS
    if
    2.41
    béco
    2.38
    what
    2.25
    You
    2.16
    jnych
    2.13
    Why
    2.09
    from
    2.03
     You
    2.03
     else
    2.00
    What
    2.00
    Activations Density 0.018%

    No Known Activations