© 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. 22-GEMMASCOPE-RES-131K
    7. 65448
    Prev
    Next
    INDEX
    Explanations

    questions starting with What

    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_22/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
     benzin
    -1.73
     klinik
    -1.66
     kompeti
    -1.62
     vokal
    -1.61
    และ
    -1.61
     berge
    -1.61
     menyen
    -1.60
     salonu
    -1.59
     calcetines
    -1.54
     necesar
    -1.54
    POSITIVE LOGITS
     do
    2.27
     does
    2.06
     is
    2.02
     if
    2.00
    '
    1.97
     did
    1.90
    ,
    1.80
     What
    1.77
     
    1.76
     Are
    1.74
    Activations Density 0.066%

    No Known Activations