© 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. 21448
    Prev
    Next
    INDEX
    Explanations

    the and a

    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
    来不及
    -1.59
    ⟣
    -1.55
    どうも
    -1.52
    ⩕
    -1.50
     trasero
    -1.47
    ふと
    -1.45
    上手く
    -1.45
     plegable
    -1.44
    なぜか
    -1.43
    ⤦
    -1.41
    POSITIVE LOGITS
     not
    2.03
     in
    1.82
     then
    1.77
     it
    1.54
     for
    1.52
    :
    1.52
    man
    1.47
     Maybe
    1.47
     Have
    1.44
    v
    1.44
    Activations Density 0.077%

    No Known Activations