© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 7078
    Prev
    Next
    INDEX
    Explanations

    interrogative words and question marks

    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
    Negative Logits
     kalau
    1.86
    elif
    1.75
     jika
    1.75
     apabila
    1.65
    specifically
    1.62
    ])+
    1.62
    unless
    1.61
    immediately
    1.59
     bila
    1.58
     if
    1.58
    POSITIVE LOGITS
     what
    2.53
     WHAT
    2.47
     무엇
    2.35
     뭐라고
    2.30
    は何
    2.24
     어떤
    2.19
    何
    2.13
    怎样的
    2.13
    what
    2.11
     What
    2.09
    Activations Density 0.023%

    No Known Activations