© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M-IT
    5. 15-GEMMASCOPE-2-RES-262K
    7. 70124
    Prev
    Next
    INDEX
    Explanations

    detects 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-it/resid_post/layer_15_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    indak
    1.87
    Integral
    1.80
     downhill
    1.80
     fared
    1.77
    ravel
    1.76
    ">{
    1.74
     calculated
    1.74
    یکٹر
    1.73
     overestimated
    1.72
     very
    1.72
    POSITIVE LOGITS
     Aufmerksamkeit
    1.38
    韓
    1.18
    ăl
    1.08
     bunting
    1.08
     potrzeby
    1.06
     nélkül
    1.02
    izure
    1.01
     houd
    0.97
    quis
    0.96
     użyt
    0.95
    Activations Density 0.000%

    No Known Activations