© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34547
    Prev
    Next
    INDEX
    Explanations

    document section markers

    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
     particuli
    -1.02
     festa
    -0.94
     fruta
    -0.88
    奥
    -0.88
    onDelete
    -0.88
    Dichloropropene
    -0.88
    Upsilon
    -0.88
     septembre
    -0.86
    lenül
    -0.85
     pese
    -0.85
    POSITIVE LOGITS
     сіль
    0.92
    なめ
    0.89
    って言
    0.88
    ったのは
    0.86
     simply
    0.85
    퐁
    0.84
    只是一个
    0.84
     tacón
    0.84
     against
    0.83
    𝓹
    0.83
    Activations Density 0.003%

    No Known Activations