© 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. 15109
    Prev
    Next
    INDEX
    Explanations

    `None`, `null`, `nil`

    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
    ppsala
    -0.96
    alline
    -0.96
     elástico
    -0.94
     forfatter
    -0.93
     visitó
    -0.90
     También
    -0.90
    domés
    -0.89
     rigue
    -0.88
     altijd
    -0.86
     fantastisk
    -0.85
    POSITIVE LOGITS
    本日の
    1.01
    ツイッター
    0.96
     semejante
    0.96
     leto
    0.93
    folded
    0.93
     `
    0.92
     韓国
    0.90
    جري
    0.90
     निम्नलिखित
    0.88
     no
    0.88
    Activations Density 0.003%

    No Known Activations