© 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. 128043
    Prev
    Next
    INDEX
    Explanations

    code structure definitions

    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
    ocirc
    -0.98
    ikbaar
    -0.98
    ochemical
    -0.90
    ложении
    -0.88
     using
    -0.88
    endaftar
    -0.85
     stanovnika
    -0.84
     смогут
    -0.82
    Doubles
    -0.82
     now
    -0.82
    POSITIVE LOGITS
    为空
    0.90
     either
    0.89
    ério
    0.86
    人民共和国
    0.85
     tantas
    0.82
     stuff
    0.82
     després
    0.82
     things
    0.81
     закон
    0.80
    で見る
    0.80
    Activations Density 0.004%

    No Known Activations