© 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. 68334
    Prev
    Next
    INDEX
    Explanations

    articles followed by important nouns

    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
    6
    -2.25
    1
    -2.23
     you
    -1.97
    3
    -1.94
    2
    -1.93
    4
    -1.82
    めっちゃ
    -1.80
     feier
    -1.80
     these
    -1.70
    7
    -1.68
    POSITIVE LOGITS
     also
    1.67
     podido
    1.57
    菝
    1.54
    .'
    1.51
     Inglaterra
    1.51
     way
    1.46
     coronel
    1.45
    También
    1.44
    ensä
    1.44
    Además
    1.43
    Activations Density 0.029%

    No Known Activations